From 91cedb5f50bd0ebc9114f52f6a3dc593df5143b1 Mon Sep 17 00:00:00 2001 From: vufg <23201083+vufg@users.noreply.github.com> Date: Fri, 19 Jan 2018 17:13:45 +0800 Subject: [PATCH 1/3] upload codes --- Lab3-policy-gradient.ipynb | 526 +++++++++++------- .../__pycache__/__init__.cpython-36.pyc | Bin 0 -> 158 bytes .../__pycache__/policy.cpython-36.pyc | Bin 0 -> 1896 bytes .../__pycache__/util.cpython-36.pyc | Bin 0 -> 1994 bytes .../__pycache__/__init__.cpython-36.pyc | Bin 0 -> 168 bytes .../baselines/__pycache__/base.cpython-36.pyc | Bin 0 -> 1372 bytes .../linear_feature_baseline.cpython-36.pyc | Bin 0 -> 2087 bytes policy_gradient/policy.py | 6 + policy_gradient/util.py | 3 + 9 files changed, 339 insertions(+), 196 deletions(-) create mode 100644 policy_gradient/__pycache__/__init__.cpython-36.pyc create mode 100644 policy_gradient/__pycache__/policy.cpython-36.pyc create mode 100644 policy_gradient/__pycache__/util.cpython-36.pyc create mode 100644 policy_gradient/baselines/__pycache__/__init__.cpython-36.pyc create mode 100644 policy_gradient/baselines/__pycache__/base.cpython-36.pyc create mode 100644 policy_gradient/baselines/__pycache__/linear_feature_baseline.cpython-36.pyc diff --git a/Lab3-policy-gradient.ipynb b/Lab3-policy-gradient.ipynb index 4529e50..3fa987a 100644 --- a/Lab3-policy-gradient.ipynb +++ b/Lab3-policy-gradient.ipynb @@ -28,17 +28,11 @@ }, { "cell_type": "code", - "execution_count": 3, - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "[2017-09-12 22:50:43,560] Making new env: CartPole-v0\n" - ] - } - ], + "execution_count": 2, + "metadata": { + "collapsed": true + }, + "outputs": [], "source": [ "import gym\n", "import tensorflow as tf\n", @@ -103,14 +97,14 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ - "/Users/andrew/miniconda2/envs/cedl/lib/python3.5/site-packages/tensorflow/python/ops/gradients_impl.py:95: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory.\n", + "/data/VSLab/vufg/miniconda3/envs/vufg_env/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py:95: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory.\n", " \"Converting sparse IndexedSlices to a dense Tensor of unknown shape. \"\n" ] } @@ -152,7 +146,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 4, "metadata": { "collapsed": true }, @@ -214,6 +208,7 @@ " Sample solution should be only 1 line.\n", " \"\"\"\n", " # YOUR CODE HERE >>>>>>\n", + " a = r - b\n", " # <<<<<<<<\n", "\n", " p[\"returns\"] = r\n", @@ -258,98 +253,74 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Iteration 1: Average Return = 14.85\n", - "Iteration 2: Average Return = 15.59\n", - "Iteration 3: Average Return = 16.61\n", - "Iteration 4: Average Return = 17.43\n", - "Iteration 5: Average Return = 17.08\n", - "Iteration 6: Average Return = 17.24\n", - "Iteration 7: Average Return = 21.3\n", - "Iteration 8: Average Return = 21.42\n", - "Iteration 9: Average Return = 20.62\n", - "Iteration 10: Average Return = 26.82\n", - "Iteration 11: Average Return = 28.0\n", - "Iteration 12: Average Return = 28.41\n", - "Iteration 13: Average Return = 28.96\n", - "Iteration 14: Average Return = 28.15\n", - "Iteration 15: Average Return = 30.64\n", - "Iteration 16: Average Return = 36.2\n", - "Iteration 17: Average Return = 38.13\n", - "Iteration 18: Average Return = 34.5\n", - "Iteration 19: Average Return = 40.37\n", - "Iteration 20: Average Return = 35.78\n", - "Iteration 21: Average Return = 47.81\n", - "Iteration 22: Average Return = 47.21\n", - "Iteration 23: Average Return = 43.34\n", - "Iteration 24: Average Return = 46.1\n", - "Iteration 25: Average Return = 50.25\n", - "Iteration 26: Average Return = 51.02\n", - "Iteration 27: Average Return = 59.81\n", - "Iteration 28: Average Return = 57.49\n", - "Iteration 29: Average Return = 61.39\n", - "Iteration 30: Average Return = 62.26\n", - "Iteration 31: Average Return = 61.98\n", - "Iteration 32: Average Return = 62.16\n", - "Iteration 33: Average Return = 59.89\n", - "Iteration 34: Average Return = 73.46\n", - "Iteration 35: Average Return = 78.51\n", - "Iteration 36: Average Return = 72.79\n", - "Iteration 37: Average Return = 78.74\n", - "Iteration 38: Average Return = 86.95\n", - "Iteration 39: Average Return = 94.08\n", - "Iteration 40: Average Return = 97.58\n", - "Iteration 41: Average Return = 103.42\n", - "Iteration 42: Average Return = 101.17\n", - "Iteration 43: Average Return = 112.39\n", - "Iteration 44: Average Return = 115.09\n", - "Iteration 45: Average Return = 134.65\n", - "Iteration 46: Average Return = 138.92\n", - "Iteration 47: Average Return = 147.15\n", - "Iteration 48: Average Return = 152.35\n", - "Iteration 49: Average Return = 149.66\n", - "Iteration 50: Average Return = 148.15\n", - "Iteration 51: Average Return = 144.82\n", - "Iteration 52: Average Return = 144.43\n", - "Iteration 53: Average Return = 153.21\n", - "Iteration 54: Average Return = 163.66\n", - "Iteration 55: Average Return = 154.28\n", - "Iteration 56: Average Return = 155.07\n", - "Iteration 57: Average Return = 161.53\n", - "Iteration 58: Average Return = 166.28\n", - "Iteration 59: Average Return = 174.05\n", - "Iteration 60: Average Return = 172.8\n", - "Iteration 61: Average Return = 170.78\n", - "Iteration 62: Average Return = 179.58\n", - "Iteration 63: Average Return = 174.84\n", - "Iteration 64: Average Return = 175.74\n", - "Iteration 65: Average Return = 174.99\n", - "Iteration 66: Average Return = 187.7\n", - "Iteration 67: Average Return = 178.94\n", - "Iteration 68: Average Return = 182.74\n", - "Iteration 69: Average Return = 181.42\n", - "Iteration 70: Average Return = 182.19\n", - "Iteration 71: Average Return = 184.58\n", - "Iteration 72: Average Return = 181.9\n", - "Iteration 73: Average Return = 184.29\n", - "Iteration 74: Average Return = 188.8\n", - "Iteration 75: Average Return = 190.46\n", - "Iteration 76: Average Return = 188.89\n", - "Iteration 77: Average Return = 187.9\n", - "Iteration 78: Average Return = 190.19\n", - "Iteration 79: Average Return = 186.28\n", - "Iteration 80: Average Return = 189.1\n", - "Iteration 81: Average Return = 188.16\n", - "Iteration 82: Average Return = 191.32\n", - "Iteration 83: Average Return = 192.03\n", - "Iteration 84: Average Return = 195.45\n", - "Solve at 84 iterations, which equals 8400 episodes.\n" + "Iteration 1: Average Return = 23.94\n", + "Iteration 2: Average Return = 29.41\n", + "Iteration 3: Average Return = 29.07\n", + "Iteration 4: Average Return = 33.33\n", + "Iteration 5: Average Return = 36.63\n", + "Iteration 6: Average Return = 41.97\n", + "Iteration 7: Average Return = 42.01\n", + "Iteration 8: Average Return = 46.57\n", + "Iteration 9: Average Return = 50.73\n", + "Iteration 10: Average Return = 56.44\n", + "Iteration 11: Average Return = 55.85\n", + "Iteration 12: Average Return = 58.21\n", + "Iteration 13: Average Return = 60.61\n", + "Iteration 14: Average Return = 62.97\n", + "Iteration 15: Average Return = 73.2\n", + "Iteration 16: Average Return = 74.45\n", + "Iteration 17: Average Return = 75.49\n", + "Iteration 18: Average Return = 93.8\n", + "Iteration 19: Average Return = 80.37\n", + "Iteration 20: Average Return = 95.74\n", + "Iteration 21: Average Return = 94.82\n", + "Iteration 22: Average Return = 95.57\n", + "Iteration 23: Average Return = 115.67\n", + "Iteration 24: Average Return = 115.55\n", + "Iteration 25: Average Return = 129.97\n", + "Iteration 26: Average Return = 135.37\n", + "Iteration 27: Average Return = 142.41\n", + "Iteration 28: Average Return = 146.57\n", + "Iteration 29: Average Return = 153.47\n", + "Iteration 30: Average Return = 151.56\n", + "Iteration 31: Average Return = 153.89\n", + "Iteration 32: Average Return = 161.93\n", + "Iteration 33: Average Return = 160.61\n", + "Iteration 34: Average Return = 161.11\n", + "Iteration 35: Average Return = 166.7\n", + "Iteration 36: Average Return = 168.21\n", + "Iteration 37: Average Return = 166.36\n", + "Iteration 38: Average Return = 169.14\n", + "Iteration 39: Average Return = 172.67\n", + "Iteration 40: Average Return = 177.67\n", + "Iteration 41: Average Return = 179.71\n", + "Iteration 42: Average Return = 181.75\n", + "Iteration 43: Average Return = 175.76\n", + "Iteration 44: Average Return = 183.49\n", + "Iteration 45: Average Return = 185.19\n", + "Iteration 46: Average Return = 187.87\n", + "Iteration 47: Average Return = 185.34\n", + "Iteration 48: Average Return = 185.09\n", + "Iteration 49: Average Return = 194.09\n", + "Iteration 50: Average Return = 187.81\n", + "Iteration 51: Average Return = 180.4\n", + "Iteration 52: Average Return = 192.99\n", + "Iteration 53: Average Return = 193.37\n", + "Iteration 54: Average Return = 192.48\n", + "Iteration 55: Average Return = 192.81\n", + "Iteration 56: Average Return = 192.75\n", + "Iteration 57: Average Return = 193.78\n", + "Iteration 58: Average Return = 194.72\n", + "Iteration 59: Average Return = 192.91\n", + "Iteration 60: Average Return = 195.15\n", + "Solve at 60 iterations, which equals 6000 episodes.\n" ] } ], @@ -371,14 +342,14 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 6, "metadata": {}, "outputs": [ { "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAZcAAAENCAYAAADDmygoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAZcAAAENCAYAAADDmygoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAASUVORK5CYII=\n", "text/plain": [ - "" + "" ] }, "metadata": {}, @@ -386,9 +357,9 @@ }, { "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAENCAYAAAD+CUlOAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nyo892QAAAABJRU5ErkJggg==\n", + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAENCAYAAAD+CUlOAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\njaRYCCGEqJEUCyGEEDWSYiGEEKJG/x/tbw2fo1NQ3gAAAABJRU5ErkJggg==\n", "text/plain": [ - "" + "" ] }, "metadata": {}, @@ -428,6 +399,123 @@ "Modify the code to compare the variance and performance before and after adding baseline. And explain wht the baseline won't introduce bias. Then, write a report about your findings and explainations. " ] }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Iteration 1: Average Return = 18.26\n", + "Iteration 2: Average Return = 17.99\n", + "Iteration 3: Average Return = 22.59\n", + "Iteration 4: Average Return = 23.06\n", + "Iteration 5: Average Return = 22.91\n", + "Iteration 6: Average Return = 24.21\n", + "Iteration 7: Average Return = 25.64\n", + "Iteration 8: Average Return = 29.37\n", + "Iteration 9: Average Return = 32.05\n", + "Iteration 10: Average Return = 32.12\n", + "Iteration 11: Average Return = 36.49\n", + "Iteration 12: Average Return = 38.94\n", + "Iteration 13: Average Return = 36.69\n", + "Iteration 14: Average Return = 37.84\n", + "Iteration 15: Average Return = 37.39\n", + "Iteration 16: Average Return = 38.23\n", + "Iteration 17: Average Return = 42.77\n", + "Iteration 18: Average Return = 45.92\n", + "Iteration 19: Average Return = 42.51\n", + "Iteration 20: Average Return = 47.85\n", + "Iteration 21: Average Return = 49.33\n", + "Iteration 22: Average Return = 46.89\n", + "Iteration 23: Average Return = 54.39\n", + "Iteration 24: Average Return = 53.58\n", + "Iteration 25: Average Return = 51.39\n", + "Iteration 26: Average Return = 53.61\n", + "Iteration 27: Average Return = 50.12\n", + "Iteration 28: Average Return = 53.24\n", + "Iteration 29: Average Return = 54.07\n", + "Iteration 30: Average Return = 54.88\n", + "Iteration 31: Average Return = 59.19\n", + "Iteration 32: Average Return = 58.64\n", + "Iteration 33: Average Return = 58.3\n", + "Iteration 34: Average Return = 56.11\n", + "Iteration 35: Average Return = 59.79\n", + "Iteration 36: Average Return = 64.27\n", + "Iteration 37: Average Return = 61.94\n", + "Iteration 38: Average Return = 62.97\n", + "Iteration 39: Average Return = 61.88\n", + "Iteration 40: Average Return = 65.74\n", + "Iteration 41: Average Return = 66.39\n", + "Iteration 42: Average Return = 71.52\n", + "Iteration 43: Average Return = 68.88\n", + "Iteration 44: Average Return = 70.66\n", + "Iteration 45: Average Return = 67.98\n", + "Iteration 46: Average Return = 72.06\n", + "Iteration 47: Average Return = 63.96\n", + "Iteration 48: Average Return = 68.72\n", + "Iteration 49: Average Return = 78.58\n", + "Iteration 50: Average Return = 77.61\n", + "Iteration 51: Average Return = 77.39\n", + "Iteration 52: Average Return = 77.69\n", + "Iteration 53: Average Return = 80.74\n", + "Iteration 54: Average Return = 78.22\n", + "Iteration 55: Average Return = 81.51\n", + "Iteration 56: Average Return = 88.52\n", + "Iteration 57: Average Return = 84.35\n", + "Iteration 58: Average Return = 92.7\n", + "Iteration 59: Average Return = 99.19\n", + "Iteration 60: Average Return = 101.56\n", + "Iteration 61: Average Return = 124.86\n", + "Iteration 62: Average Return = 122.72\n", + "Iteration 63: Average Return = 130.9\n", + "Iteration 64: Average Return = 143.11\n", + "Iteration 65: Average Return = 148.85\n", + "Iteration 66: Average Return = 160.9\n", + "Iteration 67: Average Return = 158.84\n", + "Iteration 68: Average Return = 164.05\n", + "Iteration 69: Average Return = 166.94\n", + "Iteration 70: Average Return = 162.39\n", + "Iteration 71: Average Return = 165.6\n", + "Iteration 72: Average Return = 167.21\n", + "Iteration 73: Average Return = 170.23\n", + "Iteration 74: Average Return = 168.84\n", + "Iteration 75: Average Return = 168.77\n", + "Iteration 76: Average Return = 172.72\n", + "Iteration 77: Average Return = 170.56\n", + "Iteration 78: Average Return = 181.94\n", + "Iteration 79: Average Return = 179.89\n", + "Iteration 80: Average Return = 183.08\n", + "Iteration 81: Average Return = 185.56\n", + "Iteration 82: Average Return = 185.34\n", + "Iteration 83: Average Return = 184.34\n", + "Iteration 84: Average Return = 191.06\n", + "Iteration 85: Average Return = 189.96\n", + "Iteration 86: Average Return = 190.95\n", + "Iteration 87: Average Return = 187.77\n", + "Iteration 88: Average Return = 196.36\n", + "Solve at 88 iterations, which equals 8800 episodes.\n" + ] + } + ], + "source": [ + "sess.run(tf.global_variables_initializer())\n", + "\n", + "n_iter = 200\n", + "n_episode = 100\n", + "path_length = 200\n", + "discount_rate = 0.99\n", + "baseline = None\n", + "\n", + "po = PolicyOptimizer(env, policy, baseline, n_iter, n_episode, path_length,\n", + " discount_rate)\n", + "\n", + "# Train the policy optimizer\n", + "loss_list, avg_return_list = po.train()" + ] + }, { "cell_type": "markdown", "metadata": {}, @@ -453,6 +541,61 @@ "If you answer is right, your will solve CartPole with roughly ~ 80 iterations." ] }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "# set the hyperparameter for generalized advantage estimation (GAE)\n", + "LAMBDA = 0.98 # \\lambda\n", + "class PolicyOptimizer_actor_critic(PolicyOptimizer):\n", + " def __init__(self, env, policy, baseline, n_iter, n_episode, path_length,\n", + " discount_rate=.99):\n", + " PolicyOptimizer.__init__(self, env, policy, baseline, n_iter, n_episode, path_length,\n", + " discount_rate=.99)\n", + " \n", + " def process_paths(self, paths):\n", + " for p in paths:\n", + " if self.baseline != None:\n", + " b = self.baseline.predict(p)\n", + " b[-1] = 0 # terminal state\n", + " else:\n", + " b = 0\n", + " \n", + " \"\"\"\n", + " 1. Variable `b` is the reward predicted by our baseline\n", + " 2. Calculate the advantage function via one-step bootstrap\n", + " A(s, a) = [r(s,a,s') + \\gamma*v(s')] - v(s)\n", + " 3. `target_v` specifies the target of the baseline function\n", + " \"\"\"\n", + " r = util.discount_bootstrap(p[\"rewards\"], self.discount_rate, b)\n", + " target_v = util.discount_cumsum(p[\"rewards\"], self.discount_rate)\n", + " a = r - b\n", + " \n", + " #without generalized advantage estimation\n", + " # YOUR CODE HERE >>>>>>>>\n", + " #a = util.discount(a, self.discount_rate * LAMBDA) \n", + " # <<<<<<<\n", + " p[\"returns\"] = target_v\n", + " p[\"baselines\"] = b\n", + " p[\"advantages\"] = (a - a.mean()) / (a.std() + 1e-8) # normalize\n", + "\n", + " obs = np.concatenate([ p[\"observations\"] for p in paths ])\n", + " actions = np.concatenate([ p[\"actions\"] for p in paths ])\n", + " rewards = np.concatenate([ p[\"rewards\"] for p in paths ])\n", + " advantages = np.concatenate([ p[\"advantages\"] for p in paths ])\n", + "\n", + " return dict(\n", + " observations=obs,\n", + " actions=actions,\n", + " rewards=rewards,\n", + " advantages=advantages,\n", + " )" + ] + }, { "cell_type": "markdown", "metadata": {}, @@ -523,6 +666,7 @@ " Sample solution should be only 1 line. (you can use `util.discount` in policy_gradient/util.py)\n", " \"\"\"\n", " # YOUR CODE HERE >>>>>>>>\n", + " a = util.discount(a, LAMBDA * self.discount_rate)\n", " # <<<<<<<\n", " p[\"returns\"] = target_v\n", " p[\"baselines\"] = b\n", @@ -543,7 +687,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 10, "metadata": { "scrolled": true }, @@ -552,90 +696,80 @@ "name": "stdout", "output_type": "stream", "text": [ - "Iteration 1: Average Return = 25.12\n", - "Iteration 2: Average Return = 31.17\n", - "Iteration 3: Average Return = 30.07\n", - "Iteration 4: Average Return = 31.98\n", - "Iteration 5: Average Return = 36.77\n", - "Iteration 6: Average Return = 36.22\n", - "Iteration 7: Average Return = 43.52\n", - "Iteration 8: Average Return = 45.12\n", - "Iteration 9: Average Return = 50.86\n", - "Iteration 10: Average Return = 58.81\n", - "Iteration 11: Average Return = 58.87\n", - "Iteration 12: Average Return = 65.66\n", - "Iteration 13: Average Return = 69.72\n", - "Iteration 14: Average Return = 76.32\n", - "Iteration 15: Average Return = 77.74\n", - "Iteration 16: Average Return = 78.17\n", - "Iteration 17: Average Return = 94.97\n", - "Iteration 18: Average Return = 89.34\n", - "Iteration 19: Average Return = 98.15\n", - "Iteration 20: Average Return = 103.35\n", - "Iteration 21: Average Return = 106.54\n", - "Iteration 22: Average Return = 109.03\n", - "Iteration 23: Average Return = 113.63\n", - "Iteration 24: Average Return = 119.11\n", - "Iteration 25: Average Return = 115.67\n", - "Iteration 26: Average Return = 126.51\n", - "Iteration 27: Average Return = 131.33\n", - "Iteration 28: Average Return = 138.83\n", - "Iteration 29: Average Return = 143.7\n", - "Iteration 30: Average Return = 146.15\n", - "Iteration 31: Average Return = 146.41\n", - "Iteration 32: Average Return = 157.34\n", - "Iteration 33: Average Return = 160.51\n", - "Iteration 34: Average Return = 159.67\n", - "Iteration 35: Average Return = 169.42\n", - "Iteration 36: Average Return = 170.71\n", - "Iteration 37: Average Return = 174.41\n", - "Iteration 38: Average Return = 172.93\n", - "Iteration 39: Average Return = 173.29\n", - "Iteration 40: Average Return = 177.32\n", - "Iteration 41: Average Return = 177.14\n", - "Iteration 42: Average Return = 179.85\n", - "Iteration 43: Average Return = 181.82\n", - "Iteration 44: Average Return = 182.0\n", - "Iteration 45: Average Return = 181.89\n", - "Iteration 46: Average Return = 183.19\n", - "Iteration 47: Average Return = 183.87\n", - "Iteration 48: Average Return = 183.26\n", - "Iteration 49: Average Return = 183.27\n", - "Iteration 50: Average Return = 189.11\n", - "Iteration 51: Average Return = 181.45\n", - "Iteration 52: Average Return = 186.91\n", - "Iteration 53: Average Return = 188.84\n", - "Iteration 54: Average Return = 189.76\n", - "Iteration 55: Average Return = 189.51\n", - "Iteration 56: Average Return = 186.36\n", - "Iteration 57: Average Return = 190.55\n", - "Iteration 58: Average Return = 189.35\n", - "Iteration 59: Average Return = 189.84\n", - "Iteration 60: Average Return = 187.14\n", - "Iteration 61: Average Return = 191.82\n", - "Iteration 62: Average Return = 189.32\n", - "Iteration 63: Average Return = 190.74\n", - "Iteration 64: Average Return = 188.13\n", - "Iteration 65: Average Return = 190.99\n", - "Iteration 66: Average Return = 189.23\n", - "Iteration 67: Average Return = 186.98\n", - "Iteration 68: Average Return = 188.0\n", - "Iteration 69: Average Return = 191.68\n", - "Iteration 70: Average Return = 188.03\n", - "Iteration 71: Average Return = 193.07\n", - "Iteration 72: Average Return = 191.96\n", - "Iteration 73: Average Return = 189.53\n", - "Iteration 74: Average Return = 186.71\n", - "Iteration 75: Average Return = 190.05\n", - "Iteration 76: Average Return = 191.1\n", - "Iteration 77: Average Return = 193.49\n", - "Iteration 78: Average Return = 188.66\n", - "Iteration 79: Average Return = 191.49\n", - "Iteration 80: Average Return = 191.68\n", - "Iteration 81: Average Return = 193.19\n", - "Iteration 82: Average Return = 193.87\n", - "Iteration 83: Average Return = 195.04\n", - "Solve at 83 iterations, which equals 8300 episodes.\n" + "Iteration 1: Average Return = 22.45\n", + "Iteration 2: Average Return = 22.66\n", + "Iteration 3: Average Return = 23.18\n", + "Iteration 4: Average Return = 26.35\n", + "Iteration 5: Average Return = 30.45\n", + "Iteration 6: Average Return = 31.85\n", + "Iteration 7: Average Return = 31.36\n", + "Iteration 8: Average Return = 33.17\n", + "Iteration 9: Average Return = 36.0\n", + "Iteration 10: Average Return = 39.98\n", + "Iteration 11: Average Return = 39.3\n", + "Iteration 12: Average Return = 41.77\n", + "Iteration 13: Average Return = 44.65\n", + "Iteration 14: Average Return = 45.37\n", + "Iteration 15: Average Return = 46.24\n", + "Iteration 16: Average Return = 48.56\n", + "Iteration 17: Average Return = 50.33\n", + "Iteration 18: Average Return = 51.93\n", + "Iteration 19: Average Return = 50.4\n", + "Iteration 20: Average Return = 49.76\n", + "Iteration 21: Average Return = 50.6\n", + "Iteration 22: Average Return = 56.73\n", + "Iteration 23: Average Return = 56.08\n", + "Iteration 24: Average Return = 57.1\n", + "Iteration 25: Average Return = 57.95\n", + "Iteration 26: Average Return = 59.08\n", + "Iteration 27: Average Return = 60.34\n", + "Iteration 28: Average Return = 60.77\n", + "Iteration 29: Average Return = 60.34\n", + "Iteration 30: Average Return = 62.95\n", + "Iteration 31: Average Return = 65.9\n", + "Iteration 32: Average Return = 69.17\n", + "Iteration 33: Average Return = 65.59\n", + "Iteration 34: Average Return = 64.4\n", + "Iteration 35: Average Return = 73.22\n", + "Iteration 36: Average Return = 72.33\n", + "Iteration 37: Average Return = 72.85\n", + "Iteration 38: Average Return = 75.06\n", + "Iteration 39: Average Return = 78.24\n", + "Iteration 40: Average Return = 82.66\n", + "Iteration 41: Average Return = 89.02\n", + "Iteration 42: Average Return = 92.59\n", + "Iteration 43: Average Return = 92.62\n", + "Iteration 44: Average Return = 99.64\n", + "Iteration 45: Average Return = 104.78\n", + "Iteration 46: Average Return = 104.25\n", + "Iteration 47: Average Return = 123.27\n", + "Iteration 48: Average Return = 143.53\n", + "Iteration 49: Average Return = 148.6\n", + "Iteration 50: Average Return = 165.49\n", + "Iteration 51: Average Return = 171.91\n", + "Iteration 52: Average Return = 175.98\n", + "Iteration 53: Average Return = 177.66\n", + "Iteration 54: Average Return = 176.62\n", + "Iteration 55: Average Return = 177.87\n", + "Iteration 56: Average Return = 182.12\n", + "Iteration 57: Average Return = 171.36\n", + "Iteration 58: Average Return = 170.21\n", + "Iteration 59: Average Return = 171.64\n", + "Iteration 60: Average Return = 179.67\n", + "Iteration 61: Average Return = 176.21\n", + "Iteration 62: Average Return = 182.38\n", + "Iteration 63: Average Return = 187.55\n", + "Iteration 64: Average Return = 184.0\n", + "Iteration 65: Average Return = 191.32\n", + "Iteration 66: Average Return = 192.08\n", + "Iteration 67: Average Return = 192.25\n", + "Iteration 68: Average Return = 194.47\n", + "Iteration 69: Average Return = 194.28\n", + "Iteration 70: Average Return = 193.1\n", + "Iteration 71: Average Return = 194.04\n", + "Iteration 72: Average Return = 194.81\n", + "Iteration 73: Average Return = 196.2\n", + "Solve at 73 iterations, which equals 7300 episodes.\n" ] } ], @@ -658,14 +792,14 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 11, "metadata": {}, "outputs": [ { "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAZcAAAENCAYAAADDmygoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3Xl4VNX5wPHvmYSQhMk2CRACYQubQELUoGDVIEbrbgRs\nUdGi1kqrULH+WtGithTEBeNeqKVq3RVpqlbbGpFQRTQqCUvYN8EAWWYSMtkgM+f3x00GYrZJMpmZ\nJO/neXySuXPvnXeOw7w5u9Jaa4QQQggPMvk6ACGEEN2PJBchhBAeJ8lFCCGEx0lyEUII4XGSXIQQ\nQnicJBchhBAeJ8lFCCGEx0lyEUII4XGSXIQQQnicJBchhBAeF+jrAHypoKCgXdfFxMRQXFzs4Wi6\nHykn90g5uU/Kyj2dWU5xcXFunSc1FyGEEB4nyUUIIYTHSXIRQgjhcZJchBBCeJwkFyGEEB4nyUUI\nIYTHSXIRQgjhcZJc2si55gOqP8vydRhCCOHXJLm0kV73H6r/97GvwxBCdGPOf72N873XfR1Gh0hy\naStzOM7yY76OQgjRTWmt0Z+8j/74n+jaE74Op90kubRVnzCc5WW+jkII0V0dPgjlZVBdBbu3+Tqa\ndpPk0kbKHIaW5CJEl6VrqtElhb4Oo1l65xbjF6XQW77xbTAdIMmlrfqE4bQfQ2vt60iEEG2ktcb5\nl8dw/vEu9PEaX4fTtJ1bIdICoxPRmyW59Bx9wsDhMKqsQvQA+lgp+tv16FKrr0PpuI0bYFMOVNrR\neTm+jqYRrTV651bUqPGoxDOh4Dt0SVHb7lFVia7xfeLs0Uvut4s5zPhpPwYhob6NRYh20tYiqKxA\nDRra+rnvvY7O/rfxIHYQakwSavR4GDUeFR7ZOfHVnkB/+wUqbrBbMbp1z+oqnG+9AAOHQEU5+su1\nMPFcj9zbYwoPQ5nVKNtR49DvvIje8g0q9RK3Ltda4/zTfIoq7DBpCir1EtSA+E4OummSXNpI9QlD\nA1SUQ99YX4cjRJtphwNnxoNQUojptw+jho5s+fxtm2DEWFTy2ejtm9BfrEGv/dB4ckA8anQi6vKf\noCItHY+tphr9v/+g//tPsBWjh40i4L7HO3xfAP3Bm2AtxvS7e9AbN6A/+QBdUY7qE+aR+3tCfX+L\nGjUeYgdCdD+j38XN5ELBQSg8TMDwUdSu/Qj9yfswJgnTbfd02h8CzZHk0laumku5b+MQop30+k/g\nyCEICcX5/MOY7l+Giohq+lxrERQWoKZciumiq+HH16Bra+HAbvTOreidW9CffYw+uBfTPUtQge5/\npejaE+jPssBWDOVlxkCZ3fnGv61R41Ejx6G/ykaXFKGi+3bsPX9/AJ31HupHaagRYyEoGP3fTPTX\nn7tdK/CKnVsgLAJiB6KUQiWeif7iU/SJE6hevVq9XG/LBSDydw9jtVcY/2/+8Qp63X9QV/y0s6Nv\nQPpc2qpPOAC6QpKL6Hp0TQ36vdchYQyme5ZARTnOPz+MPtH0fAq9fTMAakyS65gKDEQljMF06XQC\nfv0g6pb5sGc7+t2X2xbLV/9Dv/Zn9L/fRW/KgaIjqNFJmO59lID/W4K66jrjvI3r2/lu615Ha5yv\n/RmCQ1HTZxsH44fBgHj0hrUtX1tpR3/7hZFQf/jcke9xvrAMnfdVh+I7NU69cwuMGodSCgA1PgVq\nqmHXVvfukZ8L/eII6DcAFR6J6bJrIWEMeuMGj8TYFn5Tc8nNzeXFF1/E6XRy4YUXkp6e3uD5EydO\n8Oyzz7J3717CwsK466676NevHwD/+Mc/WLNmDSaTiZtvvpnk5OTOC1RqLqIL05+8B6VWTLf9H2rw\ncEw3/xrnikfRry+Hm+50fam5bN9kfOYHDmn2nqaJ5+LctRWd9U/0yLGoMya7F8vXn0F0P0xL/oIy\nNf47V/WPg0HD0N+sh7Sr2/Q+G7zOF2tgVz7qpjtRYcYfh0op1Nmp6MxX0SWFqOh+ja9zOnAufwS2\n5UHfWNTVN6AmngcOB/qjVeiP3oHaWvQ3n2O6436jA74jio+CtRj142knj41JhMBAo99lbMvfa7q2\nFnZuQU2+oMFxdfok9KqXmn2fncUvai5Op5OVK1dy3333kZGRweeff86hQ4canLNmzRr69OnDM888\nw+WXX85rr70GwKFDh1i/fj1PPPEE999/PytXrsTpdHZesKFm42eFzNIXXYu2H0P/+12YcBZq1DgA\nVMq5qMt+YjSfrF/T8Hyt0Ts2w+jEJr/8T6WuvQWGjsT50lPowsOtx1JRDvkbUSk/avHe6sxzYPc2\ntK3EjXfY1OvY0ategoQxqB+lNbz32anGOV9mN33th+/AtjxU2tXQOwT912U4F83H+cd56PffQJ1x\nDqZFz8PAwUbtb8eWdsXoer2dRu1EjRp/MsbewTDKzSHJ+3ZCTTXqtIZJSJ0+ybj/xi86FF9b+UVy\n2b17N7GxsfTv35/AwEDOOecccnIaDhP8+uuvmTJlCgCTJk1iy5YtaK3JycnhnHPOoVevXvTr14/Y\n2Fh2797dabGqgACjA1BqLqKL0R++A9XVmK65qcFxdfX1MHQk+t+rGs7fKjoC1iLU6CRao3r1wnT7\nb0EpnCseaXUOif72C3A4jJpAS/c980fG+e38YtSZr4C9HNP1cxolMRXTH0acht6wttG8Nb1jC/q9\nN1FnpaJ+cgumhRmon/8GjteABtOvHzI6yWMHYbrrDxDTH+czi9D7droXV2UFzpUZ6O2bTh7ctcWY\n6hA3uGGciWfCkUPooiMt3zM/F5QJRic2vL5fHAwc4vWmMb9oFrNarURHR7seR0dHs2vXrmbPCQgI\nIDQ0lPLycqxWKyNHnhztYrFYsFqbHo+flZVFVpaxovHSpUuJiYlpV7zF4RH0qj1ORDuv7ykCAwPb\nXcY9SUfKSWvduCmrCY7CwxR/+iHBUy8jYsIZjZ6vunomx55aRHjBfnpPmAhA5befUw5YJp9PoDvx\nxcRQc9dDlD78W3q9sZyIu//YbGy2vC9xxA4k+oyzW44/Jobi+GGY8r7C8pPZbSqrE7u3Yc3+NyGX\nzSD8jLOaPKfywisoX/EYkXYbvYaNAsBZaqVk5RMEDBiE5a7fYwrpY5x8+XTjvyZidPzpWWz3/RLn\nU38g6uHlBMYPazG2isz/Yt/wKfqrdYTdMo+Qy2ZQsnsbgeNPJ7Jfw6ar2vPSKHnrr4Tu3ESf08Y3\nc0ew7t6KHjGG6CFDG5WT/ZypVLz7MpZeAZiaGbzhaX6RXLwlLS2NtLSTVePi4uJ23Uf1CaO6pJgT\n7by+p4iJiWl3Gfck7S0n5wdvoj/9EHX19ahzL0KZApo8T9eewPnYfRAQyPGLr2nytfToCWAOpzTz\nDQIGGl+Mzm++gAgLtt59UO7GN2w06pqbqFn9MkWW/piunNn4tcrLcG7+BnXJdEpKWm/uciafjeOD\ntyjas4u+CSPdKivtdOB89mEIj6Tm4mnNXqPHTICAAKxLF8CgYaioaPT+XVBehmnuQqwVVVDhzoRp\nhb7rD+ilv6XkD/MxLXis+RF4DgfO99+CEadBnzDK/5pB+cYv4WgBzimXNopVB4XA6ETsq16mMnly\nk0OndWUFzp1bUZfMoLi4uNFnSo9JAqeT4jUfYTrvYjfeT/Pi4uLcOs8vmsUsFkuDD1lJSQkWi6XZ\ncxwOB5WVlYSFhTW61mq1NrrW00xhEcY8FyHcoLfloXfne/aee7aj33sTtEa/8jzOJf+H3ruj6XPf\nXgl7d2C6eR7K0vSQXtUrCHXeRZD3FbqkyOhv2b4JNSbRrZpRg3tdMg01+QL0e6/jzPmscTzfrAen\nE5Xi3gRGdea5xvtsQ9OYXvdfOLAbde0tqNA+zd/bHG70F8X0h8MHjaHR+3ejrr8d1Urto9G9Yvpj\nmrsQysuMJrKa6qZPzN0A1iJMP56G6Vf3oa6YCd8YI+JO7W9x3VcpTDN/DhUV6PfeaPqeO7cYZTp2\nQtPPxw835sx4sWnML5JLQkIChw8fprCwkNraWtavX09KSkqDc84880zWrl0LwIYNGxg3zhiul5KS\nwvr16zlx4gSFhYUcPnyYESNGdGq8prBwSS7Cbc6Xn8H54lMeW49O11Tj/FsGWGIwLV5h9AWUWXE+\n/H84//Yk2nryL1bnF58atZuLr3H1XzRHpV4KaPS6/xgr8x4rbdR+7w6lFOrGO43+jBefRO9r2MSt\nv/7MmCDo7sz7uHiIHWQkJTfoygr0P14xBiKcdX6r55suvJKA+X8k4I/PYXrmTUzPvtXuv+7VkBGY\nfvFb+G4vzhceRzsdjc5xZr1nTMBOSkGZTJiuvh7THfehLryy2TJRg4ahUn+MXvsh+vvvGj2vt+VB\nUG8YPqbp65UyOva35aKrK9v13trKL5JLQEAAt9xyC4sXL2b+/PlMnjyZ+Ph43nrrLb7++msApk6d\nit1uZ+7cuXzwwQfccMMNAMTHxzN58mTuvvtuFi9ezK233oqplZEtHaWk5iLcpG0lUFJoLOtxcK9n\n7rnqJSg6gunmu1AhoZjOTsW06HnUj6ehc9bhXDgH5z9eMSY5vvqc8SU77aZW76ui+0HSRGOG/JZv\njWNjWu/Mb/JevXph+uUCCI/EmfGAqwajS63GcNmU89yuESmljFFjO7ZQ8/Xn6NwvcW5Ya3yhNkF/\n+i+otGO69pa217qUQgW2PlmxxXtMmIi67hdGLfD1FehTRq/qfbtg9zbUhVc2aMZUyZMwzbyt2aZN\nAHXVDRAcgvOtFxoPQMjPNebHtDDRUp0+yRg6vfnbDrw79/lNn8sZZ5zBGWc07Gj86U9PzigNCgri\n7rvvbvLaadOmMW3atCaf6wymsAioqkTX1rZpRrLoefQp+3HonM9QgxM6dr8t36LXfoi6ON1Y36uO\nCg5FzZiNnnIp+h+voj98xxgdFmnB9It7UAHNf2mdyjTlMpx5X6H/9TZE90N1YIkjFR6J6Z7Fxl/w\nf3kU57Zc6DsAtEa1cU0vlXIu+l9vU7r4/1zHNBh/8SdPOnmsuhL98T8haSJqSMfKuiNMF1yG01pk\nDP2uroLZ81CBvdBZ70FIKOpHF7b5niosHHXVDeg3/wJ5X0Ld+9bWYjhyyGjWbMmI04zZ/xu/8Mqa\navLN2A6msAjjl8pyCPfOyAvRRe3ZZjRXJIxB5/wPPe2mNv81XU8fs+F8+WljPa/0WU2eo2L6o277\nDfqiq9CfvI+aeiWqLZ/RscnQbwAUHnbNj+gIFdMf0/89jH7/DfRHq0BrGDgE9YPhtq3eZ9BQTPc9\nTkRIMGU1xyEoGOdfHsX52gpMo5NQdYvI6k8/gopyTF5e6qQpatpNEBJqLL9yrBTTdbejv/kMdcEV\nqOD2LXqrUi9BZ3+E882/ogoOGkOXjxhzAlubZKlMAcb6cDn/c3s5mY7wi2axrsZUN8tX5rqI1ujd\n22DYKGPCXkkh7G/fHCxdZsP5+O+N5p5b70b1CmrxfDV0pHHesJYXpWx0nclU1/eCMTvcA1RgIKZr\nbsQ0/4/QLw419fL23WfYKILGn4EaMgI1YBCmG++AMis681WgbtHLjzNh3OmoumHFvqSUwnTZtaib\nfw07t+D8013g1O1+/1BXlrN+CdVVRtJ69XmjNhQVA3HNr6Lgun7SBagLLoMTnb8kv9Rc2kHV11wk\nuYgW6OoqOLgXdckMVPIkdMDz6K//1+YvfF1agnPZ78FWgmneQ53e3KNSLwWnA3XGOZ6972kTCFi8\n3HP3Gz4aNeUy9Kf/Qk+agt6VbwwhvqLx8GdfMp1zITo8EufyR1BnTO5QUyMYI8oCnnzNmKhaaYcK\nO5jDW11Fwbh2nGt1hs4myaUdXM1i0qkvWrJvpzE8dMRpqD5mGJuM/voz9IybXU1j2umg9tB+CDY3\neQttLTYSS5kN068fQo0c2+lhq969UZc0MVnQD6lrbkRv3IDz5WeMPZbGJKFGnObrsBpR48/E9PBf\noXdvz90zqLfR5BoZ3frJPiDNYu1Q3yym7bK+mGie3rMNlIKE0QDGUifWYqibj6Jra3GueIySudfj\nfO+NxiOADh/C+dgCOGbDNP8PXkksXY0KCcV0/e3w/QEjAftZreVUKizcSAg9hNRc2qF+ZVUq7b4N\nRPg1vXsbxA1G1S12qpLPRgf2Quf8D4Yk4PzLY7BxA71GjePE+29AVQVcewvKZELv2Izz+SUQEIjp\n7j+1uSmtJ1GnT0Kdd7Gxs+bo5pdHEd4lyaUdVHAoBARKn4tolnY6YO8O1MSTk/hUSCiMPwP9zefG\nvui5G1AzbyPq2p9R9PwjRsdsVQV6xFj0q3+GfgMwzV3Y4Tb6nsB0052+DkH8gCSXdlBKGXtcSJ+L\naE7Bd1BVacwtOIVKORed+6WRWK77BaapVxgjtH76cwg1o99/Az7/xNia9pf3umo9QnQ1klzaq0+Y\n9LmIZtVPnvxh57KacJaxodbZUzCdsr2uUgp11XU4o6Kh6DDqqus7PFNcCF+S5NJeUnMRLdm9DSKi\njAURT6GCQwj47dJmL+voirVC+AsZLdZesmGYaIHevQ0STmv3bHwhujpJLu2kzLIysmiaLjUWq/TH\n+RZCeIskl/aqq7l4ahl10Y00098iRE8iyaW9zGHgqIUad3apEz2J3pUPQUHGBk1C9FCSXNqrfoio\n9LuIH9A7NsOIsbIdg+jRJLm0kzLXzdKvkFn64iR9rBS+P4Bqxw6OQnQnklzaq0+Y8bNC5rqIk/SO\nLUD7d3AUoruQ5NJeZiO5aGkWE6fasQmCQ2DICF9HIoRPSXJpL3N9zUWSizhJ79gMI8e5va2wEN2V\nz3sc7XY7GRkZFBUV0bdvX+bPn4/Z3Hg9pbVr17J69WoApk2bxpQpUwB44403WLduHXa7nVdeecV7\ngYfWJRepufRIeucWY1fFSMvJY6UlcOR7Y4VeIXo4n9dcMjMzSUxM5OmnnyYxMZHMzMxG59jtdlat\nWsWSJUtYsmQJq1atwm43OtLPPPNMlixZ4u2wjZFAIaFSc+mBnOs/wfnYfThfeLzBcb19MwBqtPS3\nCOHz5JKTk0NqaioAqamp5OTkNDonNzeXpKQkzGYzZrOZpKQkcnNzARg1ahRRUVFejdmlT5ix+53o\nMfTGDeiXn4HwSNi5xdWBD8COzRDaB+KH+iw+IfyFz5NLWVmZKzlERkZSVlbW6Byr1Up09MmtPC0W\nC1ar1WsxNqtPGFpqLj2G3paH8y+PwpARmB4yEozzX2+dfH77Jhg1HmWS/hYhvNLnsmjRIkpLSxsd\nnzmz4ZakSqlOXegvKyuLrKwsAJYuXUpMTEy77hMYGEhMTAy2KAtOeznR7bxPd1dfTt3BiV352J5f\nQmDcYKL+8DSmsHAqpt2I/aVnCC8qICC6L8XFRwm7+jpC2/ieu1M5dTYpK/f4Qzl5JbksXLiw2eci\nIiKw2WxERUVhs9kIDw9vdI7FYiE/P9/12Gq1MnZs2/cTT0tLIy0tzfW4uLi4zfcAiImJobi4GGdQ\nMLrsu3bfp7urL6euTjudOJ/+E4Sacc59AGvNcagpRqecB+/+HdtrK1w7TlYMGk5lG99zdyknb5Cy\nck9nllNcXJxb5/m8WSwlJYXs7GwAsrOzmThxYqNzkpOTycvLw263Y7fbycvLIzk52duhNtZH9nTp\nETZ9BYf2o66+ocHoMNU7GHVxOmzdaGxRbA6HuME+DFQI/+Hz5JKens6mTZuYN28emzdvJj09HYA9\ne/awfPlyAMxmM9OnT2fBggUsWLCAGTNmuIYrv/rqq8yZM4fjx48zZ84c3n77be8Fbw6Dygq0w+G9\n1xRepbXG+cHb0DcWdXZqo+fVlEuNPzIO7UONTkSZfP5PSgi/4PN5LmFhYTzwwAONjickJJCQkOB6\nPHXqVKZOndrovFmzZjFr1qxOjbFZfeqa8CrtEBbhmxiER2it0Z99bCSIfgNOPrHlWziwG3XTnU1O\njFTBoaiLrkZnvgpjZD0xIer5PLl0aeZTJlJKcunS9Nefo//+LDrCguk3f0INGFRXa3kTLH1Rky9o\n9lp14ZVw/DjqrPO9GLEQ/k3q8B2gZPHKbkGfOI5+9yUYEA/aiXPZ/ejDB2FbHuzdgbp0OiqwV7PX\nq+AQTNfMQoU2XllCiJ5Kai4dYZYlYLoD/fE/oaQQ0z2Ljbkrj9+P8/H7ISIKIi2oH6W1fhMhRANS\nc+mIPvUrI0vNpavSpVb0h6vg9ElGf8uAeEz3LAGl4OA+1CXTUb2CfB2mEF2O1Fw6IjzS+FkuyaWr\n0pmvQu0JTDNudh1TAwZhumcJ+su1sgilEO0kyaUDVO9g6B0MxxqvPiD8nz6wB73+E9RF6Q1HiAEq\ndiDq6ht8FJkQXZ80i3VUWIQkly7K+d7r0CcMdflPfB2KEN2OJJeOCo9El0ty6Wq00wm7tqJSfoQK\n7ePrcITodiS5dJTUXLqmwsNQVSnbEQvRSSS5dJAKj4TyxtsECP+m9+8CQA0d6dtAhOimJLl0VHgk\nlB9DO2V9sS7lwG4ICjImTgohPE6SS0eFRYJ2ykTKLkbv3wXxw5tcL0wI0XGSXDrKNddFmsa6Cu1w\nwHd7kSYxITqPJJcOUvXJRTr1u47DB+F4DQyVznwhOoskl44KN1ZD1pJcugx9YDcgnflCdCZJLh3l\nahaT5NJl7N8FIaHQz73tWoUQbSfJpaNCzRAQIM1iXYjevxsGJ8iukUJ0IvnX1UFKKZlI2YXo2hPG\nlsTS3yJEp5Lk4gnhkehjMlqsS/j+ANTWwhDpbxGiM0ly8YTwSKm5dBF6f31nvtRchOhMPl9y3263\nk5GRQVFREX379mX+/PmYzY23i127di2rV68GYNq0aUyZMoWamhqeeOIJjh49islk4swzz+SGG7y/\nTLoKi0AXHPT664p22L/L2EE0pr+vIxGiW/N5zSUzM5PExESefvppEhMTyczMbHSO3W5n1apVLFmy\nhCVLlrBq1SrsdjsAV155JU8++SSPPvooO3bsYOPGjd5+C66ai9ba+68t2kTv3w1DRhh9ZUKITuPz\n5JKTk0NqaioAqamp5OTkNDonNzeXpKQkzGYzZrOZpKQkcnNz6d27N+PHjwcgMDCQYcOGUVJS4tX4\nAWMJmNoTxiq7wm/pmhooOICS/hYhOp3Pk0tZWRlRUVEAREZGUlbWuGPcarUSHR3temyxWLBarQ3O\nqaio4JtvviExMbFzA26KLAHTNRzaB04napj0twjR2bzS57Jo0SJKSxt3eM+cObPBY6VUu5orHA4H\nTz31FJdeein9+zfflp6VlUVWVhYAS5cuJSYmps2vBUYt6dRra+IHUwpEKE1QO+/ZHf2wnHytckMB\n5YDl9LMJiPafuPytnPyZlJV7/KGcvJJcFi5c2OxzERER2Gw2oqKisNlshIeHNzrHYrGQn5/vemy1\nWhk7dqzr8YoVK4iNjeXyyy9vMY60tDTS0tJcj4uLi9vyNlxiYmIaXKudRkIsO3gA1W9gu+7ZHf2w\nnDqDzvsKfXAvpitmtnquc2suRFiwOkF1clxt4Y1y6i6krNzTmeUUF+feyhY+bxZLSUkhOzsbgOzs\nbCZOnNjonOTkZPLy8rDb7djtdvLy8khOTgbgzTffpLKyktmzZ3sz7IbqmsVku2Pv0xvWoj9c5dZ+\nOnrfLhg2SjrzhfACnw9FTk9PJyMjgzVr1riGIgPs2bOHjz/+mDlz5mA2m5k+fToLFiwAYMaMGZjN\nZkpKSli9ejUDBw7kd7/7HQCXXHIJF154oXffRJixeKXMdfE+XV4GJ45DSRH0jW3+vAo7HP0edc5U\nL0YnRM/l8+QSFhbGAw880Oh4QkICCQkJrsdTp05l6tSGXwzR0dG8/fbbnR5ja1RAgDF3QpKL99mP\nGT+PHGoxuXCgblvjYaO8EJQQwufNYt1GWKTxV7Twrrrkog8favE0vc9ILgyRkWJCeIMkF0+RJWC8\nTmvdsObS0rn7dkLsIFRoHy9EJoSQ5OIhKjwSZPFK76qqAIfRkd9SzUVrDft2oobJ5EkhvEWSi6eE\nR8qGYd5WX2vpHdxyzcVWbNQqpb9FCK+R5OIpYRFQVYk+cdzXkfQc5XXJJWEM2I+h6x//UF1/ixoq\nyUUIb5Hk4in1S8BI05j31NVc1Ii6CbXN1F70vp0QGAiDhnopMCGEJBcPUa7kIk1j3qLrk8tII7no\nw01ve6D374L44ahevbwWmxA9nSQXT5GJlN5XP/R7yAjoFdRkzUU7HbB/N2qodOYL4U2SXDxFloDx\nPvsxCOwFwSHQfyD6yPeNzzn8PdRUSWe+EF4mycVTwqRZzOvsxyAswlhNe8AgaKJZTO/bASDDkIXw\nMkkuHqJ694beIbKnixfp8mPGsjsAsYOgpBB9vKbhSft2QUgf6OfeSq5CCM+Q5OJJ4RFSc/GmupoL\nAAMGgdZQWNDgFL1/JwwdgTLJR10Ib5J/cZ4UHomW5OI95WUos7H/jxowCGg4U18fr4FD+2WxSiF8\nQJKLJ4VFSrOYN9nLoS650C8OlIJTk0tejrGtccIYHwUoRM8lycWDlCxe6TW6ttZYWyysruYS1Bui\n+7mGI2uHA/3e6zAgHsaf4ctQheiR3E4uW7ZsobCwEACbzcazzz7L888/T2mpfJm6hEcay5A4Wt8V\nUXRQ/bpi5lO2xR4Q72oW0xvWwpFDmNJnoUwB3o9PiB7O7eSycuVKTHWdon//+99xOBwopVixYkWn\nBdflREQZncrWIl9H0v3Vz86v79AHVOxAOPo9+sRx9PtvGJMrT5/kqwiF6NHc3onSarUSExODw+Eg\nLy+P559/nsDAQG6//fbOjK9LUSPHogG9fROqpV0RRcfV922dWnOJHQQnjqMzX4WSQkw33oFSyjfx\nCdHDuV1zCQkJobS0lPz8fAYNGkRwcDAAtbW1nRZclxM3GCKj0Vu/9XUk3Z62lxu/mE+puQyIN577\n+J8wajyMTfZFaEII2lBzueSSS1iwYAG1tbXMnj0bgO3btzNw4MAOBWC328nIyKCoqIi+ffsyf/58\nzGZzo/PWrl3L6tWrAZg2bRpTpkwBYPHixZSWluJwOBgzZgw///nPXc133qaUQo1LRm/cgHY4UAHS\n1t9p7HWKgB70AAAgAElEQVQ1l7Cwk8dijeHIaI3pmllSaxHCh9xOLunp6Zx11lmYTCZiY40mH4vF\nwpw5czoUQGZmJomJiaSnp5OZmUlmZiazZs1qcI7dbmfVqlUsXboUgHvvvZeUlBTMZjPz588nNDQU\nrTXLli3jiy++4Ec/+lGHYuqQcWfC55/A/l3GPiOic9Tv3RJ6MrmosHCIjIb4YSeX4RdC+ESb/sSP\ni4tzJZYtW7ZQWlrK4MGDOxRATk4OqampAKSmppKTk9PonNzcXJKSkjCbzZjNZpKSksjNzQUgNDQU\nAIfDQW1trc//WlVjJ4AyobdI01insh+DUDMqsOHfR6bfLcX0i3t8FJQQop7byeXBBx9k+/btgFHb\neOqpp3jqqadcTVXtVVZWRlRUFACRkZGUlTWehGi1WomOjnY9tlgsWK1W1+PFixdz2223ERISwqRJ\nvh0dpPqEwdAR0u/S2ezHGnbm11Ex/VHBoT4ISAhxKrebxQ4ePMioUcYyGp988gkPPvggwcHBLFy4\nkGnTprV47aJFi5qcDzNz5swGj5VS7ap53H///Rw/fpynn36aLVu2kJSU1OR5WVlZZGVlAbB06VJi\nYmLa/FoAgYGBLV5rn3guFatewtI7CFNY4y/AnqK1cuoIW00V2hKNpZPu702dWU7djZSVe/yhnNxO\nLlprAI4cOQLAoEFG52lFRUWr1y5cuLDZ5yIiIrDZbERFRWGz2QgPb/xlbLFYyM/Pdz22Wq2MHduw\nTT0oKIiJEyeSk5PTbHJJS0sjLS3N9bi4uLjV2JsSExPT4rV62GhwOin+bA2miee26zW6g9bKqSMc\n1mKI7tdp9/emziyn7kbKyj2dWU5xce6tMO52s9jo0aP529/+xiuvvMLEiRMBI9GEnTpapx1SUlLI\nzs4GIDs723XvUyUnJ5OXl4fdbsdut5OXl0dycjLV1dXYbDbA6HP59ttvOzx6zSOGjTKWeZemsc5j\nP+ZatFII4X/crrnccccdvP/++4SHh3PVVVcBUFBQwGWXXdahANLT08nIyGDNmjWuocgAe/bs4eOP\nP2bOnDmYzWamT5/OggULAJgxYwZms5nS0lIeffRRTpw4gdaacePGcdFFF3UoHk9QAQEwdgJ660a0\n1j4fZNDdaK0bLrcvhPA7Ste3d/VABQUFrZ/UBHeqnM7//Rf992cxPfQMauCQdr1OV9dZVXNdVYlz\n3kzUjJsx/fgaj9/f26Spx31SVu7xh2Yxt2sutbW1rF69mnXr1rn6SM4//3ymTZtGYKDbt+kx1LjT\njaVgtn7bY5NLp6lftLIHD5YQwt+5nRVeffVV9uzZw2233Ubfvn0pKiri3XffpbKy0jVjX5ykLH2N\nVXq35sLFXf+va79St66Y9LkI4b/c7tDfsGEDv/3tb5kwYQJxcXFMmDCBe+65hy+++KIz4+vSVMIY\nOLjX12F0P66ai/S5COGv3E4uPbhrpv3iBkN5GVp2p/QoXd7EXi5CCL/idrPY5MmTeeSRR5gxY4ar\ns+jdd9/1+Yx4f6YGxKMBDh+Uv7I9qamNwoQQfsXt5DJr1izeffddVq5cic1mw2KxcM455zBjxozO\njK9ri6tbAr7gIGrUeB8H043Yj0FgIASH+DoSIUQzWkwuW7ZsafB43LhxjBs3rsHcje3btzN+vHxx\nNikqBnqHGDUX4TnlZWAOl/lDQvixFpPLn//85yaP1/+jrk8yzz77rOcj6waUUhAXjy74ztehdCva\nfqzBJmFCCP/TYnJ57rnnvBVHt6Xi4mX5fU+zH5M5LkL4Od9s2diTDBgMZTZ0RbmvI+k+ymVdMSH8\nnSSXTqbqOvWl38WDmtnLRQjhPyS5dLYBJ0eMiY7TtbVQaZfkIoSfk+TS2Sx9Iai31Fw8pbKueVHm\nDQnh1yS5dDJlMhlrjMmIMc+Q2flCdAmSXLxAxcWDNIt5Rt3sfCWjxYTwa5JcvGHAYCgtQVe2viW0\naJn+/oDxS4TFt4EIIVokycULZMSYZ2inA/3J+zB0JMT6wXbWQohmSXLxhvoRY5JcOmbjBig8jOmS\n6bL0ixB+TpKLN8T0g6Agqbl0gNYa50fvQr84OP1sX4cjhGiFJBcvUKYAiB3U7UeM6Zrqzrv59k1w\nYDfqx+lGeQoh/JrbS+53FrvdTkZGBkVFRfTt25f58+djNpsbnbd27VpWr14NwLRp05gyZUqD5x95\n5BEKCwtZtmyZN8JuMzUgHr0r39dhdBq9exvOR34HY5IwXXQ1jD/To/d3/ns1hEeiJk/16H2FEJ3D\n5zWXzMxMEhMTefrpp0lMTCQzM7PROXa7nVWrVrFkyRKWLFnCqlWrsNvtrue//PJLgoODvRl22w2I\nB2sRurrS15F0Cl1QN4rr+wM4n1mE88E7qP4syzP3/m4v5G9EpV2F6hXkkXsKITqXz5NLTk4Oqamp\nAKSmppKTk9PonNzcXJKSkjCbzZjNZpKSksjNzQWgurqaDz74gOnTp3s17rZScYONXw5/79tAOktZ\nKQCmh/+K+vlvoFcQZRkPob/b0+Fb6/+shuAQVOolHb6XEMI7fJ5cysrKiIqKAiAyMpKyssb7zVut\nVqKjo12PLRYLVqsVgDfffJMrr7ySoCA//4u2Lrnow9203+WYDcxhqN69MZ2diumexZjCInC++me0\n09nu2+rv9qJzPkOdfwkqtHFzqRDCP3mlz2XRokWUlpY2Oj5z5swGj5VSbRpiun//fo4ePcrs2bMp\nLCxs9fysrCyysoymmqVLlxITE+P2a50qMDCwzdfqqCgKAwMJOWYjrJ2v689KqyqpjYo5pVxiOH7r\nXdieeJA+uV8QevHVbb6ndjiwPvoXCI8getbtmLrprPz2fJ56Kikr9/hDOXkluSxcuLDZ5yIiIrDZ\nbERFRWGz2QgPb/wFYrFYyM8/2RlutVoZO3YsO3fuZO/evdxxxx04HA7Kysp46KGHeOihh5p8rbS0\nNNLS0lyPi4uL2/V+YmJi2ndthIWq7w9S087X9WeO4qNgDm9QLtHnpsEH71D+8nNUjByPauNik85P\n/4XelY/6+W+w1hyHmu5XbtCBz1MPJGXlns4sp7i4OLfO83mzWEpKCtnZ2QBkZ2czceLERuckJyeT\nl5eH3W7HbreTl5dHcnIyF198MStWrOC5557jj3/8I3Fxcc0mFr8QaUGXlvg6is5RZkNFRDU4pJTC\ndMMcqKlCv/tym26nS0vQq/8OY5NRZ53vyUiFEF7g8+SSnp7Opk2bmDdvHps3byY9PR2APXv2sHz5\ncgDMZjPTp09nwYIFLFiwgBkzZjQ5XNnvRVqgGyYXrbXR5xIe1eg5FTcYdVE6+vMs9G73h2I733wB\namsx3TBHZuML0QX5fJ5LWFgYDzzwQKPjCQkJJCQkuB5PnTqVqVObn+PQr18/v53jUk9FRqO3bPR1\nGJ5XXQXHj0NEZJNPqyt+aiSXNf9CjRjb6u30phz4Zj0qfRaqn3tVcCGEf/F5zaVHiYo2moiqutlc\nlzKb8bOJmguA6h0MI8eiD+xu9Vb68EGcLz4FA+JRP77Gk1EKIbxIkos3RdYNp+5uTWN1yeWHfS6n\nUoMToPBwi9sO6OKjOJ94AEwmTHfejwrs5fFQhRDeIcnFi1R9crF1r+Sij7VccwFQQ+qaOA/ubfoe\nZTacGQ/A8WpM8/8gzWFCdHGSXLwpytjgqtuNGKtvFmumzwWAwUZy0Qcaz9jXlXacTz4IpVZM8x5E\nDRrWGVEKIbxIkos3ddOaC8dsEBAILcygV+GREBUDTSWXj/8J33+H6Vf3oRLGdGakQggvkeTiRSqo\nt/EFXGr1dSieVVZqrFhsauXjNCShybXG9NaNMGwkatzpnRSgEMLbJLl4W1R0t2sW08dsEN5Ck1gd\nNTgBjn7fYGVoXWGH/btRY5M7M0QhhJdJcvG2SEv3axYrs0ELI8XqqcEJoDUc3H/y4PZNoJ2osVJr\nEaI7keTiZSoyuvs1ix0rbXEYssuQ+k79k/NddH4uBIfAsFGdFZ0QwgckuXhbVDQcK0U7HL6OxCO0\n0wHHytyruURajPNO6XfR23JhdCIq0OeLRQghPEiSi7dFRoN2nhy+29XZjxnvp4U5Lg0MTnANR9ZF\nR6DoCOo06W8RoruR5OJlqrvN0i+tn53feoc+1E2mPHwIXVNjNImBdOYL0Q1JcvG2uomU3Sa5uDE7\n/1RGp74TDu0zkktUDMQO7MQAhRC+IMnF2+pqLtrWPTr1dVndDqPudOjDyU79/btg+ybU2AmypL4Q\n3ZAkF28zhxuz2btdzcW9ZjGiYsAcjv7ff6HSDtLfIkS3JMnFy5TJ1L02DSuzQXCIsay+G5RSRu3l\n+wPG49MmdGZ0QggfkeTiC5EWdHeZSHms1P2RYnVU3SKWxA8z1hwTQnQ7klx8IdLSbSZS6jJby6sh\nN0ENGWH8lFFiQnRbklx8wJilX2LsPd/VHbOh2lhzYdQ4GDQUdVZq58QkhPA5mRbtC1HRUFMNVZUQ\n2sfX0XRMWSmMs7TpEhUWQcCDT3dSQEIIf+Dz5GK328nIyKCoqIi+ffsyf/58zObG+4KsXbuW1atX\nAzBt2jSmTJkCwEMPPYTNZiMoKAiA3//+90RERHgt/nY5dSJlF04u+ngNVFW4P1JMCNFj+Dy5ZGZm\nkpiYSHp6OpmZmWRmZjJr1qwG59jtdlatWsXSpUsBuPfee0lJSXEloXnz5pGQkOD12NtLRUajwUgu\ncYN9HU77uXagbGOzmBCi2/N5n0tOTg6pqUbbe2pqKjk5OY3Oyc3NJSkpCbPZjNlsJikpidzcXG+H\n6jn12x139YmUx4wJlG3ucxFCdHs+r7mUlZURFWV8OUVGRlJWVtboHKvVSnR0tOuxxWLBaj35xfz8\n889jMpk4++yzmT59erMzvrOyssjKygJg6dKlxMTEtCvmwMDAdl8LoMPCKARCj1dh7sB9fK16t4My\nIHLIUHo18T46Wk49hZST+6Ss3OMP5eSV5LJo0SJKS0sbHZ85c2aDx0qpNi8FMm/ePCwWC1VVVSxb\ntox169a5akI/lJaWRlpamutxcXFxm16rXkxMTLuvdQk1U1lwkOq6++hvv0Dv2orppz/v2H29yHnI\nmAhZ6lSoJsrDI+XUA0g5uU/Kyj2dWU5xcXFuneeV5LJw4cJmn4uIiMBmsxEVFYXNZiM8PLzRORaL\nhfz8fNdjq9XK2LFjXc8BhISEcO6557J79+5mk4tfiYp2TaTU1mKcLz0FVZXoK2eiQhsPaPBLZaWg\nFIT5+QAKIYTX+bzPJSUlhezsbACys7OZOHFio3OSk5PJy8vDbrdjt9vJy8sjOTkZh8PBsWPHAKit\nreWbb74hPj7eq/G3W91ESq01zlefN4YlAxzY0/J1/uSYDczhqIAAX0cihPAzPu9zSU9PJyMjgzVr\n1riGIgPs2bOHjz/+mDlz5mA2m5k+fToLFiwAYMaMGZjNZqqrq1m8eDEOhwOn00liYmKDZi9/piKj\n0Yf2o79cC5u/Rl32E/SHb6O/2+PR9bZ0dRX68yzUlMs8ngSM2fnSmS+EaMznySUsLIwHHnig0fGE\nhIQGw4unTp3K1KlTG5wTHBzMI4880ukxdor67Y7f/CskjEFdfR16w6cer7noT95HZ76KGhAPnl5u\npR3rigkhegafN4v1WJHRoDXUVGH62VyUKQCGJKAP7PbYS2iHA73u38bvhw+1/fq9O3C+8Dj6xImm\nTyizub0DpRCiZ5Hk4iMquq/x88rrjFoFdQs6Fh5GV1Z45kU25YC1bsTI4e/afLn+ap3xX87/Gj/n\ndBp9LhFtW/pFCNEzSHLxldOSMd25EHXJNNchVbdLI995pmnMufZDY3OuYaPaV3Opi0Nn/bPRIpv6\n68+gthY1dKQnQhVCdDOSXHxEBQSgJkw0msPq1S1Frz3Q76KPfA/5uajzf4waOAQOH2zb9U4nfLfP\nWDfs4D7YueWU5xzo9980lq45fVKHYxVCdD+SXPyICosASwx4oN9Fr/0QAgJR518MA+KhvAxdfsz9\nGxQehpoq1BU/BXM4zo//efLeX/0PjhzCdNX1xs6aQgjxA/LN4G8Gj+hwzUXXVKPXr0GdeQ4qPMrV\np9OW2os+uBcAlXAaKvUS2JSDLiwwBgm8/yYMGia1FiFEsyS5+Bk1JAEKCzrUqa+/zIaqCtSUy4wD\ncUZy0Ufa0DR2YA8EBkJcvHEfUwA6631jXk5hAaarr5NaixCiWfLt4GfqtwCmruYAoEsKcdx/O3p3\nfjNXNaTXfgiDhsKI04wDUTEQ1BsK2lBz+W4PxA1BBfZCRVpQZ52HXv8J+r03YHACTDjb7XsJIXoe\nSS7+pm7E2KnzXXTmq8YQ5c3ftHq5riiHg/tQZ6W6FgFVJhMMiHd7xJjWGg7uPTl6DVBpVxu7Z5YU\nGn0tbVxgVAjRs/h8hr5oSIVHGjWNun4X/d0e9Ia1rt9bdbTAuM+AQQ3vO2AQeseWpq5ozFoM9nKI\nH37y+sHDYfwZUF0NSSnu3UcI0WNJcvFHQxJcnfrOd1+GPmEwahzs3obWusVag65LLvT/wbLYA+Jh\nw1p0VSUqJLTl1z9ovLYaPLzBYdMdvwdafn0hhABpFvNLakgCHP0e/c16Y67K5T9BjUmC8jKwtbJH\nQ2EBKBPExDa8Z/2IsSOtN43pA3uNewwa1vAegYGowF5tei9CiJ5Jkosfqu/Ud/79GYjuZ6xoXN/R\n31rT2NECiO6L6vWDJFCXXLQbw5H1d3sgdiCqd+82xy6EECDJxT/Vd6RXVqDSZxmJYtAwUKZW58Do\nwsPQr4md4vrGGkOL3Rkx9l3DznwhhGgrSS5+SIVHQXQ/GDwcddb5xrHevWHAoBaTi9Yajn6P6j+g\n8T0DAqD/QHQrzWL6mA1KSxp05gshRFtJh76fMv36QQgJbTBRUQ1JQOfnNn9ReSlUV0H/gU0+rWIH\ntT7i7Lu9rtcSQoj2kpqLn1ID4lGR0Q0PDhkBZTZ0aUnTFx09bFzbVLMYGP0uxYXo4zXNvq6uSy7E\nD2v2HCGEaI0kly5EDa6rTRzY2+TzurB+GHLjZjHAWAZGO11zYZq8x3d7oG8sKtTckVCFED2cJJeu\nJH4YKNX8bpVHCyAgAKL7N/l0/cTKFkeMfbcXBkt/ixCiY3ze52K328nIyKCoqIi+ffsyf/58zObG\nfzWvXbuW1atXAzBt2jSmTJkCQG1tLStXriQ/Px+lFDNnzmTSpO65Wq8KDjE65ZvpN9FHCyC6v9F5\n35T+A435K80kF11ZAUVHUD9K81TIQogeyufJJTMzk8TERNLT08nMzCQzM5NZs2Y1OMdut7Nq1SqW\nLl0KwL333ktKSgpms5nVq1cTERHBU089hdPpxG63++JteI0aktD8Mi6FBY1n5p96ba8g6Nu/+ZrL\n/p3GebK7pBCig3zeLJaTk0NqaioAqamp5OTkNDonNzeXpKQkzGYzZrOZpKQkcnONUVOffvop6enp\nAJhMJsLDw70XvC8MGQGlJcaQ4VNoraHwMKqF5AIYnfrNzHXRu/KNmk3CaE9FK4TooXxecykrKyMq\nKgqAyMhIysrKGp1jtVqJjj45cspisWC1WqmoMPY8eeutt8jPz6d///7ccsstREZGeid4H1CDE9Bg\ndOonnnnyiVIrHK9pegLlqdfHD0dv+hpdYUf1adj8qHflQ/wwVHAra48JIUQrvJJcFi1aRGlpaaPj\nM2fObPBYKdWmRREdDgclJSWMHj2an/3sZ3zwwQe88sorzJ07t8nzs7KyyMrKAmDp0qXExMS04V2c\nFBgY2O5rO8oZOpEiIKS4AHPMj13Hjx/5DhsQMXIMvVuI7fjk87F98CZhBfsJnjzFdVzX1lK4bych\nF11FuIfemy/LqSuRcnKflJV7/KGcvJJcFi5c2OxzERER2Gw2oqKisNlsTTZrWSwW8vNPbpRltVoZ\nO3YsYWFh9O7dm7POOguASZMmsWbNmmZfKy0tjbS0k53VxcWtLALZjJiYmHZf6xH9B1KxbTPVp8Tg\n3GmUz7EQM6qF2LQlFnqHcOzLddhHjj95fN9OOF5DzaBhHntvPi+nLkLKyX1SVu7pzHKKi2ul6b2O\nz/tcUlJSyM7OBiA7O5uJEyc2Oic5OZm8vDzsdjt2u528vDySk5NRSnHmmWe6Es+WLVsYNGhQo+u7\nGzV4uGu/F5ejhyGwl7EXTEvXBgbC6PGNZvrrXXXJu373SiGE6ACfJ5f09HQ2bdrEvHnz2Lx5s6tz\nfs+ePSxfvhwAs9nM9OnTWbBgAQsWLGDGjBmu4co33HAD77zzDvfccw/r1q3jpptu8tl78ZqhI8Fa\n1GDUly4sMCY/urGvvRqbDEVH0EVHTl6/O9+4/oerAgghRDv4vEM/LCyMBx54oNHxhIQEEhJOrm81\ndepUpk6d2ui8vn378oc//KFTY/Q3avIF6PfeQP/zddSc3xkHj7Y8DLnB9WOT0YDelofqG2uMNNu9\nDTX+jM4LWgjRo/i85iLaToVFoC66Cv3N58Y2yE4HFB1ufk2xH4odBJHRUN80drTA2IhsxNjOC1oI\n0aNIcumi1EXpEGrGmfmased9ba37NReljNrL9k1opwO9a6txfOS4zgxZCNGDSHLpolRoH9Sl02Hz\n1+j1nxjH3EwuAIxNhopyYy2x3dvAHAaxTS/VL4QQbSXJpQtTF1wBEVHoD98xDrjbLAao05IAo99F\n786HEWPbNMdICCFaIsmlC1O9e6Mu/yk4HBDUGyIt7l8bHgWDhqK/zDaWjZH+FiGEB0ly6eLUeRcZ\nWyLHDmpzzUONTYbvDxi/y/wWIYQH+XwosugYFdgL0/w/Gh36bb32tGT0fzOhVxDItsZCCA+S5NIN\ntKkj/1Qjx0FgIAwbhQrs5dmghBA9miSXHkz17o2a+QtU31hfhyKE6GYkufRwptRLfB2CEKIbkg59\nIYQQHifJRQghhMdJchFCCOFxklyEEEJ4nCQXIYQQHifJRQghhMdJchFCCOFxklyEEEJ4nNJaa18H\nIYQQonuRmks73Hvvvb4OoUuQcnKPlJP7pKzc4w/lJMlFCCGEx0lyEUII4XGSXNohLS3N1yF0CVJO\n7pFycp+UlXv8oZykQ18IIYTHSc1FCCGEx8l+Lm2Qm5vLiy++iNPp5MILLyQ9Pd3XIfmN4uJinnvu\nOUpLS1FKkZaWxmWXXYbdbicjI4OioiL69u3L/PnzMZvNvg7X55xOJ/feey8Wi4V7772XwsJCnnzy\nScrLyxk+fDhz584lMLBn//OsqKhg+fLlHDx4EKUUv/zlL4mLi5PP0w988MEHrFmzBqUU8fHx/OpX\nv6K0tNTnnyepubjJ6XSycuVK7rvvPjIyMvj88885dOiQr8PyGwEBAdx4441kZGSwePFi/vOf/3Do\n0CEyMzNJTEzk6aefJjExkczMTF+H6hc+/PBDBg4c6Hr86quvcvnll/PMM8/Qp08f1qxZ48Po/MOL\nL75IcnIyTz75JI899hgDBw6Uz9MPWK1WPvroI5YuXcqyZctwOp2sX7/eLz5PklzctHv3bmJjY+nf\nvz+BgYGcc8455OTk+DosvxEVFcXw4cMBCAkJYeDAgVitVnJyckhNTQUgNTVVygwoKSnh22+/5cIL\nLwRAa83WrVuZNGkSAFOmTOnx5VRZWcm2bduYOnUqAIGBgfTp00c+T01wOp0cP34ch8PB8ePHiYyM\n9IvPU8+ud7eB1WolOjra9Tg6Oppdu3b5MCL/VVhYyL59+xgxYgRlZWVERUUBEBkZSVlZmY+j872X\nXnqJWbNmUVVVBUB5eTmhoaEEBAQAYLFYsFqtvgzR5woLCwkPD+f555/nwIEDDB8+nNmzZ8vn6Qcs\nFgtXXnklv/zlLwkKCmLChAkMHz7cLz5PUnMRHlVdXc2yZcuYPXs2oaGhDZ5TSqGU8lFk/uGbb74h\nIiLCVcsTTXM4HOzbt4+LL76YRx99lN69ezdqApPPE9jtdnJycnjuuedYsWIF1dXV5Obm+josQGou\nbrNYLJSUlLgel5SUYLFYfBiR/6mtrWXZsmWcd955nH322QBERERgs9mIiorCZrMRHh7u4yh9a8eO\nHXz99dds3LiR48ePU1VVxUsvvURlZSUOh4OAgACsVmuP/2xFR0cTHR3NyJEjAZg0aRKZmZnyefqB\nzZs3069fP1c5nH322ezYscMvPk9Sc3FTQkIChw8fprCwkNraWtavX09KSoqvw/IbWmuWL1/OwIED\nueKKK1zHU1JSyM7OBiA7O5uJEyf6KkS/cP3117N8+XKee+457rrrLsaPH8+8efMYN24cGzZsAGDt\n2rU9/rMVGRlJdHQ0BQUFgPElOmjQIPk8/UBMTAy7du2ipqYGrbWrnPzh8ySTKNvg22+/5eWXX8bp\ndHLBBRcwbdo0X4fkN7Zv384DDzzA4MGDXU0V1113HSNHjiQjI4Pi4mIZOvoDW7du5f333+fee+/l\n6NGjPPnkk9jtdoYNG8bcuXPp1auXr0P0qf3797N8+XJqa2vp168fv/rVr9Bay+fpB95++23Wr19P\nQEAAQ4cOZc6cOVitVp9/niS5CCGE8DhpFhNCCOFxklyEEEJ4nCQXIYQQHifJRQghhMdJchFCCOFx\nklyEcMPdd9/N1q1bffLaxcXF3HjjjTidTp+8vhDtIUORhWiDt99+myNHjjBv3rxOe4077riD22+/\nnaSkpE57DSE6m9RchPAih8Ph6xCE8AqpuQjhhjvuuINbbrmFxx9/HDCWgI+NjeWxxx6jsrKSl19+\nmY0bN6KU4oILLuAnP/kJJpOJtWvX8sknn5CQkMC6deu4+OKLmTJlCitWrODAgQMopZgwYQK33nor\nffr04ZlnnuGzzz4jMDAQk8nEjBkzmDx5MnfeeSdvvPGGa62oF154ge3bt2M2m7n66qtde6a//fbb\nHDp0iKCgIL766itiYmK44447SEhIACAzM5OPPvqIqqoqoqKi+PnPf05iYqLPylV0X7JwpRBu6tWr\nF33NSBIAAAMxSURBVNdcc02jZrHnnnuOiIgInn76aWpqali6dCnR0dFcdNFFAOzatYtzzjmHF154\nAYfDgdVq5ZprruG0006jqqqKZcuW8c477zB79mzmzp3L9u3bGzSLFRYWNojjqaeeIj4+nhUrVlBQ\nUMCiRYuIjY1l/PjxgLHy8m9+8xt+9atf8eabb/K3v/2NxYsXU1BQwH/+8x8efvhhLBYLhYWF0o8j\nOo00iwnRAaWlpWzcuJHZs2cTHBxMREQEl19+OevXr3edExUVxaWXXkpAQABBQUHExsaSlJREr169\nCA8P5/LLLyc/P9+t1ysuLmb79u3ccMMNBAUFMXToUC688ELXYo4AY8aM4YwzzsBkMnH++eezf/9+\nAEwmEydOnODQoUOu9bpiY2M9Wh5C1JOaixAdUFxcjMPh4Be/+IXrmNa6wcZyMTExDa4pLS3lpZde\nYtu2bVRXV+N0Ot1efNFms2E2mwkJCWlw/z179rgeR0REuH4PCgrixIkTOBwOYmNjmT17Nu+88w6H\nDh1iwoQJ3HTTTT1+eX/ROSS5CNEGP9ycKjo6msDAQFauXOna+a81b7zxBgDLli3DbDbz1Vdf8be/\n/c2ta6OiorDb7VRVVbkSTHFxsdsJ4txzz+Xcc8+lsrKSv/zlL7z22mvMnTvXrWuFaAtpFhOiDSIi\nIigqKnL1VURFRTFhwgT+/ve/U1lZidPp5MiRIy02c1VVVREcHExoaChWq5X333+/wfORkZGN+lnq\nxcTEMHr0aF5//XWOHz/OgQMH+PTTTznvvPNajb2goIAtW7Zw4sQJgoKCCAoK6vE7OYrOI8lFiDaY\nPHkyALfeeiu/+93vALjzzjupra3l7rvv5uabb+aJJ57AZrM1e49rr72Wffv28bOf/YyHH36Ys846\nq8Hz6enpvPvuu8yePZv33nuv0fW//vWvKSoq4vbbb+fxxx/n2muvdWtOzIkTJ3jttde49dZbue22\n2zh27BjXX399W96+EG6TochCCCE8TmouQgghPE6SixBCCI+T5CKEEMLjJLkIIYTwOEkuQgghPE6S\nixBCCI+T5CKEEMLjJLkIIYTwOEkuQgghPO7/AdYWXsNU6TlEAAAAAElFTkSuQmCC\n", + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAZ0AAAENCAYAAADUubjhAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRwghhMdI0RFCCOEx/wESM6tyyrVcFwAAAABJRU5ErkJggg==\n", "text/plain": [ - "" + "" ] }, "metadata": {}, @@ -673,9 +807,9 @@ }, { "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAENCAYAAAD+CUlOAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nyo892QAAAABJRU5ErkJggg==\n", + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAENCAYAAAD+CUlOAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\njZJiIYQQolH/H9zJFPYWwfuXAAAAAElFTkSuQmCC\n", "text/plain": [ - "" + "" ] }, "metadata": {}, @@ -713,7 +847,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.5.3" + "version": "3.6.2" } }, "nbformat": 4, diff --git a/policy_gradient/__pycache__/__init__.cpython-36.pyc b/policy_gradient/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fc8c8dc7a9b23fe19607dd777c3dff57d5b9465c GIT binary patch literal 158 zcmXr!<>hkoPKaUvg2x~N1{i@12OutH0TL+;!3>&=ek&P@K*9*(m$!aOVo9QYSg=oG zl73lfTDrcotBa3*Mt*K;d45s0v2H zFQmM2{11K!|G|&&)W5(B%s9C!qLw@!k7wt5W*>CB+4q0`G+G`I@;BL8A>fZ-o0|Y6 zk+dWu>Q6Qbz9y2%;0=+13fI9XlJprFgl~b9oa6{E7X#!GY%fK52_q({WN*kQkbw;0 z3}qx^I3t;Wl+;~$EE+Ybb&-qmySgm$Wgc(k?Zb)qV-$Id64H<PfI*U*CuPa zN^L4z@IroNV|GkdEqLomgnKq!Q`tHuYxeGz9g_pH$}DP%J_QV3_F-QEDcuQOGn=j1 zstuIBZOis`0vbASy9)fV?Hs_pO;%mFCDQ}jh1Z_P4{c9&(67~=ZGk`6Eb#E_b`Ri@ zBoNl#iR;uajM8VKDeB4$n2XG*m@5}nVy0Xo@(rEp2!iV}A0>TIW44A)xAOJ z;-Z=_8snlxRlt$qR~w0&&$g`hHROi8MKJm7x4VD+zI^h~rHvLv#q0Uoe_;)d9c#v} zJugMBPU})C?UHd>i{`<7*X6smx~Qm-n)0oYuFZGM3qfS#B5ss1E-uAVX)q8BHp;Q8 za$zH?QZcL)g@23CNDWo-;%Eq>|kVBdvCm1B$@m&I(9)QiR=*(R=tyB7FR%!+d~ z1|5MM=@d-V9ker=YY50F-l!QJZsNcT`P%StDVj!AN{(8di=V07rQiq0>!@WGT6?ox z4_z=^RFa})%xXw+jHNE zw=bhG+}z&6VX3Ggi-mQGj!y)O-P5cbIv zt!u51fYAkdQRxo=(^v7zs=15v#mp>bE5Y`|Tw2a^wo$p8@6r$=E1Q9VC=KWf04V~}v+xWq*GfZYcKf&xPmg9JO6APg|KG33H_8-PjJKKIq374%_sMge3}P%VoLHQ@jPqG77bW5y&VOEra`U3^q1G=D zJVJmKz5_6v8Vd^TGCn{w{V{EO8feI%olLD^7`@W?$8k}$n9Y~^6U5{C#Z={u=iQO% URroxmpKpwMh||xzl+rZ%4`71;kpKVy literal 0 HcmV?d00001 diff --git a/policy_gradient/__pycache__/util.cpython-36.pyc b/policy_gradient/__pycache__/util.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2f4660893d595511dc2fd5d3e28c02fc12b87b3d GIT binary patch literal 1994 zcmZ8hOK%)S5T2gbuE)E!6Cy&SNVGsg9^$N%m{SxWkVIS}A215ihG^Y8-8-Jmyy)(+ zcf=KmS+#CBadwEcVsMJF#oLZ>xprKh0Dkg%*b~F}-}2 z4e}_XgH(yPoS#@FleWBG+DXwL+#GJ)|rDRN8N4!yPv^M2y%~;75SBL z2kg3sZ$5oip3WP*%e$#$JQJnf@8ro^ZgiH9>ZKXZa;CK?CsutQbgKvkheTumJ#^(3NC|q1 zEx70wt0@TDnG@}{&I+(Nce~ZOx7gKQ>#fLB=hf|Vzja#wmZSZ7(2~|)xi_5FZT&~i z&-6!pAGR*U9x~)N?-uAecQ0fQWx&=ye1{==_YX9=1FN_vA^RK?yb-ce#>+)%0?Eo$ z7{6fp#CUaeX2PT?R8z!(Aqz9)kO@^&>WO4pn8Bqe_(YnZYzml2X0h#tAsX1eyf*1{ zp>c)yJ7kOWq2DGqh`bGQf|QXR;Ft;)9zs{!H+~|RY|Lvb#2O&$g@(c z9T**e{m~aVJm}o`Ug$=a>LFzm5U!V$Ny(OUNx!6WS55RD+f$QY^qu?XF}*`O-#&ja z(R6Jcp`g2nge?uUooQHCP0q2*>$`-QR@F7KywLW}!xM4ZH(HXu?I#rXn}tvYUH~or+nO8Xq7#GeMG9 zO2oeLk#mgqS}aW;xKxyYdc&j84z8lvb1Em z!~n#ub^A(vcSZ7kX#1C;J%C5bav+iSPysoNKQK|cEJl_$m8J5IxsgrkWrz5{+8$jo zEpNbcc^3wA4Y&${%CjjjaTkehmY?8xp!6~q#%q+YBy5SsW|PIvI&#Hh8v{#Q{YOQ` Zn_PT_Nv+V}4gfwNJ4otoAKOl}`7hdX?oa># literal 0 HcmV?d00001 diff --git a/policy_gradient/baselines/__pycache__/__init__.cpython-36.pyc b/policy_gradient/baselines/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..cc718f6a0e0423a5cfd1edb8822591f94d2007c2 GIT binary patch literal 168 zcmXr!<>hkoPKaUvg2x~N1{i@12OutH0TL+;!3>&=ek&P@K*9*(SEznUVo9QYSg=oG zl73lfTDrcotBa3*Mt*K;d45s0v2HlIYq;;_lhPbtkwwF6mK48#lo!-^}v literal 0 HcmV?d00001 diff --git a/policy_gradient/baselines/__pycache__/base.cpython-36.pyc b/policy_gradient/baselines/__pycache__/base.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d4468aaf2f66f41c497629bba3b76d792dc78a13 GIT binary patch literal 1372 zcmbVM&2rN)5SD+EIB7z|lT5R zOf0Z3$;b)OQx6Ac$0)@cRGeT8nb?4lcVyyl7aVZ!$gMSLK?~Zr*M<&wXgkn_9$F7} zppUi-19*hC2fK(dEWKB(;7OeE5E+`Gt(Fs%qKE3nx*-%9V!SmTS(7eJA*V&o!;xLO z`0rWi@$Aa%{3KFm_WOMROtIkO<#5ht~&@WDxUA z1=X6?>*Seqq>Hu@?^d-=SE+#b7~fQKh2@&m7JRmO5}EY#aH zPk4&?b2yVy$p5e!MqC*_DZOIJf}3kum*82=ry2FvmDZ*Bhl$iXBiq!YbP%9flwr|; zAJpZrmiO?@sE5F}a;D}*lYlde)o=r|U#EPCONqsjF5rvpVnJ82o7W;Jy?(%7!LL+EA+R=|HV=1S!>`|HuSR{Jhr}XQBC6!0& z<}bZm3Z$;CWk=(8wc622_k!HjO5e~1FAC+9c#NrXIJlk{nuIE%g;~V35q%EeO UF?X}xc1Y>HsOY`arxhsV5BzB=-T(jq literal 0 HcmV?d00001 diff --git a/policy_gradient/baselines/__pycache__/linear_feature_baseline.cpython-36.pyc b/policy_gradient/baselines/__pycache__/linear_feature_baseline.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1bcd97999615c1f2bd69850c09cfd3b3cbf96107 GIT binary patch literal 2087 zcmah~%WfMt6eT$ijbu47VmFDdgIyiAG+VVguEhe zeb6WSQ1l}(f(V+DA?;F11QSlmy3SWbxWc<6!jp9BbY0;bkNEb5h)|ZpN5>*FpuSHw%lDEG(I^@Ugvr(_#KKSzK zVf!Q>%9pu%@npNm(2Ei$DS4$L|eXG#YyNYkA%;k{2T zTp0C0R807rWa3Uh##oEmCVKNHAnzWV(!LKe4}NAKyS0vK=Eqv9GhQZnre~JxnvyTM z5?W!n`cUBeZhwaC&5$~HV=n(O(aB%e*Vi*B*I~`DtT1kzCWUcQnHe8KmGz|oU;2a> z(yYaK7V}bOP>h>rQit9=-UTmD49yKq4Fj%`hPNVLUx?AZ9E}no^bT#(yL9~F>cB5| zEa^qHqQ(%u9)Ll5enOuYgP#tHDSh zTnxw-xd*S=&O=Zz94&H1qPkU--}%=YKq#9C<1Uy!yn^peB78Rx@d?;g6u5cy=hy_%L@Qts@gdCXJ22aUzfchDW7 zt1U1VUGoBUNLr-A2Em7zLcYtYHwv%z6If~i-Uyxg6ejMYvkI5hld=kGD8#ECfH8iW zWIXK~FV&?!HS}xah`dxaoC^{G`6?;Tjb~+4B?`9^j)%h0-5MsVAurWu=n~blAj+!Q zfomhx8s9LX_vsd7t&c!I6&bb&w zPzkKUk&t!N9oQB67P!5%@y1f+TD4%@Mp%WoqDp?NXf(A#Ns+`QYQSbrLL2Y`#viQ4 zKVRJe7BH)Xb$`~#w` B;En(Q literal 0 HcmV?d00001 diff --git a/policy_gradient/policy.py b/policy_gradient/policy.py index 99fecf3..bf26f32 100644 --- a/policy_gradient/policy.py +++ b/policy_gradient/policy.py @@ -31,6 +31,11 @@ def __init__(self, in_dim, out_dim, hidden_dim, optimizer, session): """ # YOUR CODE HERE >>>>>> # <<<<<<<< + hidden1 = tf.layers.dense(inputs=self._observations, units=hidden_dim, activation=tf.nn.tanh, name='hidden1') + #hidden2 = tf.layers.dense(inputs=hidden1, units=out_dim, activation=tf.nn.tanh, name='hidden2') + #mistake tf.nn.tanh as the activation function for the second layer + hidden2 = tf.layers.dense(inputs=hidden1, units=out_dim, activation=None, name='hidden2') + probs = tf.nn.softmax(hidden2) # -------------------------------------------------- # This operation (variable) is used when choosing action during data sampling phase @@ -72,6 +77,7 @@ def __init__(self, in_dim, out_dim, hidden_dim, optimizer, session): Sample solution is about 1~3 lines. """ # YOUR CODE HERE >>>>>> + surr_loss = -tf.reduce_mean(self._advantages * log_prob) # <<<<<<<< grads_and_vars = self._opt.compute_gradients(surr_loss) diff --git a/policy_gradient/util.py b/policy_gradient/util.py index 61ef302..184a93d 100644 --- a/policy_gradient/util.py +++ b/policy_gradient/util.py @@ -32,6 +32,9 @@ def discount_bootstrap(x, discount_rate, b): Sample code should be about 3 lines """ # YOUR CODE >>>>>>>>>>>>>>>>>>> + b[0] = 0 + return x + discount_rate * np.roll(b, -1) + # <<<<<<<<<<<<<<<<<<<<<<<<<<<< def plot_curve(data, key, filename=None): From 2f66b50c5e8bff6e31f4f284b3c02ad41cdd0575 Mon Sep 17 00:00:00 2001 From: vufg <23201083+vufg@users.noreply.github.com> Date: Fri, 19 Jan 2018 20:24:51 +0800 Subject: [PATCH 2/3] Add files via upload --- imgs/tanh.png | Bin 0 -> 21762 bytes imgs/wrong-award.png | Bin 0 -> 16921 bytes imgs/wrong-loss.png | Bin 0 -> 19203 bytes report.md | 21 +++++++++++++++++++-- 4 files changed, 19 insertions(+), 2 deletions(-) create mode 100644 imgs/tanh.png create mode 100644 imgs/wrong-award.png create mode 100644 imgs/wrong-loss.png diff --git a/imgs/tanh.png b/imgs/tanh.png new file mode 100644 index 0000000000000000000000000000000000000000..649af8ba4ca7be498bd4d4bc2e13a8879fe76633 GIT binary patch literal 21762 zcmb5WWmuG7^fo$lcXx;&jg&(ONC*PbBAp`L-5}j9Al;xyh|=9TfFRu<14>FW#M%7* zZ=Cb-z%>^z@jQF4xYxa66Q!mikB3c-4S_)LUMa|GKp;rn4-ZUq@QfejkR14dZl)wJ z3%P&z&TlJAfj}4`uVi0nd1db{d-`d;xw}7}ef^kpmr?FB=?kgPCTP9iv|eo4VvwS> zS2Z^t=*{IJ{}G=3*1YO&Kln$FTuy4og3 zl+25h;|zKJ6oEWMX45MP*YP$uEg{kWkFSb#t`3sOMAlBM05&FO=KdSpy|2S0n+1fz z7#~r}u5%(IBPmZroOql%4`mD0Db^xaUnzv5&M85%Am+C!CA5L)&D62?gMg)8}9iO6%EQE$9mq`h2;j+e5`9RO2~#tB{enq+XqKz@tvCC3l=46+Ikn+3=_j>)8yFWYR+7xhZjPlH zH;XDRj_Q9Exb={ypLaTRxF+p9yyx*C>qQHG`?h*}n^b()B`c1U@S9dqUX5?IQ;@Y# zl(6Th%ofpqRNa}=-q&{B@+{!28}u9>KBM%_@r}_NHyG$&e!WAcyta=P!1hR86|6-` z*ij>bXL=?{O1#c)L1-DRvq7SaSttm*p!XvdE%FQ^C;ZZqNf7b}1$EswZz_pe3XUmv zELl{+S1BrfY^&akr^x(!Y2>WInSb!c`(jPMU*)(FVC&?eSpPK<2q zHZ|GtU=i;T5jih^9%;uEyNqOhZr7y@UcUqODIaCWAM&4T3Urov&sN4}1Iiu=g}{gu z_pr$EKdZ9D)prKoDwpB1zKwu*&6(^SF6mFd!vDFRf$)#ues}dLcA8R@Idx7Tc^^6z z6ijv|FseZLWA3GKkPk+|^2_#9F@_2%EzHN~I&-A43^+e0XAM{if4c18Ic=!ykyFb& zAu9$79NwjWo!>U@o%&lZKdkFg0I&Z5IrbT4$M8Rr9Cu8b!)*mgsJ4+W(S(R})EnWf z8i<$;&brGe{&_&3$)0^i4sQN1>-gs4?HN^a>OgbCt;$OqTr%mX*W|pW$0FpbmpO`5 z$^_@aA}05VzA>V0?ZpLR8FvDK0!g1_fwrffXd`pps>m>pc%-j>d(!HnQ*0nA57b33 zWf*ddK^41<2^TjNtX8C&iB1fg+#qoK56}%v`2x~tKmS!$ zQ@dbXyoJfxkmo!~owKMV$s*0i5&kH4ruW?ouMXwU>%2!x)_eiKxtY$Sa_c_H*DY6` ziP2T)0!yqN;i1(sO2;jl%6!wO!Z>T@8$HNU-A2g*M))&u(cU$iX0$bf#3NY=dzCk%22+~ zAvM*&9^NtuRAw){YU<37mA&W5(I?omx5xGsuU`d)nkLrR8s!^w$^E(DW#*&J!mo?k zg}K1Rgku_NMUee|gLiWY)831O)Hav|{5(=@`r{q12Wv2H-E-v7K&c>9w4>=m2`FRS z)+NnF5pMbu-uooy5owan1XXAFJwUK&agI>ty9}i4cYJpt=;jv?R&Yl$LkKaDz?=Lk zb)vvgG<=%ad*6`SS#>8N2U1KZr-~qI%^S=TY%So=ral^0DQ{J_%{=&n6l?SA#4ObK z^uyGOwLZD&vxK`}avpm4q5A&8#LJ2_2TyG^@>9MFDtUL*x>^wm#j#}4)qF`A>(4wf zZgQhIzZz6UBih~ma_?M>q9Suzh~qe)$%#o@>#L#~P91}+Elq4r+<{n%thq(PlGO1kdZWpu{3JmR(zuf|3v_66RMocatEvJ zkI4;oZC5vUXnj0p3H5_!oJs58-<4H3GgL`Og+A?8uBcOVf@RwPd>{(+GlAZjh13SR zIktZ*Xldc__Yk%_eMXbCQ~Ihw&P;6_;qAEeZZAT#ZsyRS*Yg+9oO~#;B>5D1mTiso z(34U`_G|y_Gt3j*KF8Rmk_?R?t+o7u%indiGwuDIyuQ*WIaVLlD;}KgGD+UwZW}U% zInfKZt3uPGj15fhnllVKM&C?#e7f(dseo?P5yfTfnnbPoaF1kNc?oYRVk|e5m6NAg z5qJalKf30Oo1U$*Y)^7Z5&_48{VjTj>{L+;^nPp(73oB0{IpG*#!=p}O4UC39*5=k zN!;p{!dR*FljD9WFMA67-jCEzo+jKu?CS}|iP}#9+Rg*CZP)SJ4cOmzWqsttWA*em zbx7?ZBm}RYH~n`k(^hZJ&0IoxrlhtFaF^6e;w>ev&eFK?%$v~p7rXj+{jmNevI??) zqwcL89TIf^NWAYwBuSDo^1(eHM?D*YlfJxe_xZ3Z_ij~~(l_1rM05Nafpj?v7iU2) zCsg#Kf+4L1ty(MmvUu?i-!onvr{Rl!F|}K~S}()c)0Sah+mPBRKHq?o#(EjcY@}Nj zV6>FwgwdDgv=h@NH`eIp4H!ItABaC+u9h@J74sXFF$-;eDR*<+2)M)B@(cSP7+=Z> zuSLs^%_8D4<%+j;Mxzq$dDHzC7~&tF{8-&puv247y(C@Z;%|zQqt-Dl+H$>4HlElW z??8LdG%H6aaW#G4wmLD@?$kN&3pgg{SC}abd8dX*BmS5{(j{@O2yAs|1LvZ}NW!9q z-qNI*-8gl%c=#M83&>DYu}TwDbw!GgXzVG+dO?f@i_w)K=4;QtUj-?Bt9@e{AGv1_ z{nU4~7;qXqeuNSA9E8WqcPC8zYwjP!xv3R925wdK-A3DutIc`+o3MPP>|0b-VRAfwo|tOuSEU{G2n4a?J@gNI%me8$JloXqfgN3Qf0y)S z=|btbJ(8!**gWVf<4?~YdjK8WQ1|HrEG4siVSKUp+I-#8I3+2g5P)O_J2rN~N2BB# z4Zu$Z$e^5R8T>sadnv){z{*P!5O0$kE_+U4&!dQeR(g(14 zz9|s=Bxg|Mar+Z0GA#~r`?y!#*dDWy{d1RnqG4^whaix*X;v0Z9D;UCCGyYd4B?0< zLlAFe=6?eWOVfbRKx;WvXNU@V8~U=t$I$J_Yf{OHmRv0PM2q5vDmMS1?Bn)d=qb;d zzk>O?|3m-ATyGdf1GKz~e?sPj8DvgGr?X0sz1xjTWy9y8nIF-0*@uU0)rzqYFdjj) zRMm?GsDdNOVAG;qX}QT{KivD@+{b2q)Qf!#k9);=_eXT z6_t9N*i+o~KQc1d~EiW1zY$0w1u?lajX$uta$bz(yYEVpg zZEJQ#2qC}&$1|Deg38BOlh$L1W$agAU9`Wi!zDmE~$Yi>D+6Wnhx zQ~T>(fK^A>@0SgaodHQN?j-!znd30#!s;WekmA6wstYOe!$I|4J*xljVqPNh48m}l z6<7e{IN&!F8(U^x?=y?V1CX2+;3mMu--A1Pwfzp*r(X~ADUlLogFhBI^iQasdrB>Q zm6O~nOeUSA=B^v(`u)B0=*~v{?PPariEZD7z@g<;YFWV;`HFBo9Z@>#GC7t|s5tTx z(v3pR(auEZb;d2i){f5un>EHuG9J&3XHdPNTp`2ir+pIjJ1jS@3@hIxeL}h60uYW^ zJhn8UZokW(9(}DIQZN81KvKC`SLVTN+Q$=i(; z7gJzS0PMEXdY}#Yh;ly~)?o`vD{BMUr-?|)@c`GKPC@wmpXj)ZfM-zcK#++^))Pn75wLl9f zN_=2WyMLX6=q^S)n$Tpu!rX)Zq~dfwLaGrE%!<{D>nDmPS0bdnUb#8mnI8O3lMc;f z>Mwc}BfyOnLqodW@7nww}%wE2iw6PbLg5`v^iO(xQc^7XyKd<0L|?#!3)fnfVzuXmvV zmVD>bYkf9y3TuIoYyaps2uyEbE&wv4 zx2$yCgujXNttmHBEk1S4?FZw0Az?&$iQb7XrBXT{g~lRbRi&O3Nj=ohC####WRVPM z=cDwMtZ5QO;_}?4p;@8FLUbpkD!i$9$k2?b;yZqt?6n_>iv&zX zK^85?TbpK0`B(h}+)WlRO~0S$mT5kkqBOCF6jr*smTfQ1?YK-@5rblYxLN@~)iA`d zej8@lxB7=Ae_)WMlls|(WKAV6Q~&kxU4A$v0ICZ;=WY{mDo#;eCMJU z+Ri}rjPM2WY1f&r(Bz#~Pv&+ICl%hrnLV38t-<`q*)bJm^TGkesxAy=xdX{$-3hv8 ztHR6!yzNho*V3(zP&HM~PV=^2@2gJKpyO(2iaW-7Ui&r+u{6L&(fA{ASYxwba#I!Y zcx>LQ29hgd#-?+k^SoOm@}r)>HEzwJD6Nmc7TlHB2#;EQ55pC?##7~>+TOg2i|FQu zg@v1pITz-{opRMF>04aiPpfqa1(P!s$N*K-N*|MfjtIDKF;cua(*65X?9AA0luIB~ z{2%4C83u2h;g%cS;?ak$CD~%qPqtd4BU>KG*>F$lNe+lAS|=<>6(p@@8b7wF;Pdb=znmK?nRo(`M>etS{;~ZN*a^T$oBV(^gBR9=Y9X~*$j>i~IXR(~hKj+*VT3c>BV;L$keARx0KKZoB?bg@WIU;xgl^IBoLJLotHu zJ;*`A3dvYnKRO{FiRD`?_uv*pR_|*XIY!6DbB20HzExB}(eNU#CTK z@VnN-->7Wx8vH58Py8F$tTHt3RwqnJ!0?4AoWgbz#j?ax6a9Y`F_Ip;pQ}90qs4*(euxF#33Z$#HL8C_IwLdWe<}Ofj4P{RM-lHS zBV?0n2M^W$GB5!CNP`Fv#iW`HG%WH_k3$|>yw%Ih1O+(|h%e1WDRaEHB|>UjklvC8 z*6_w6HE+`5t(ZF@m`zInaf#?^jjH?E!p<7OWw(LllQbl$^Mcz6hKKCgBB?q%nLo_} z)R#oQW)?8UK`t<{rd>}RlRc!S=RzZ_DY7&AxS6saxeUpJFu>7nkr^Z^(Xv1Nh=av~ zU!r=aL2_9-1_fAbqvEB*<@%505%#o~fxJ1-~v zI=G~GYN_*McL(30^nxjgiKP2{CpmEwNUrvSvVv5kROpw;&-bG#L7qlz-7`PTIm(od zB85S$Bh8A})0#G88uwAfHCYG!J7dK2)=ooQ%URnAO3NQuc3ysVw0LAma{xg%B2+JF z@ER#C`Tt1FnHuM;H`TmU+O{-7NqjBv@|c|$O5n-{%PvF^o2ckCurr$$Wm>TKpfzSd zT88+1)|I_LoJ2w=T{6VnM|OfjJWA2WV>&(y)hUaE>}Y43>%IQwyKZJrjvsg@W3Vg^ zja(ZtY4g{?9V-Ds@{zBQ|oR<6JgWfwA2Bc4^zqatLpbP;{3FyWZW&zCWr0MdZuY-g-9Zb-i zLOOOMwH5*x4;#6!UBtw6$b5{dh|jgIsgTf}Bj3!8qHdd-r_JnfUB3C``sPoP_~mOd z7m_Frp&x|Xkih=TA+wV4rpVA$4ZSsG-5DC4SFHCYuQDQJNp%#&kVjD@AU?=VI<4b- z$zgnSJ_}A5L3karPFPWB;PdpT+epS5D`hrGJ8tAE7goDGW*Atw=g2%<5I8 zs>pxe-o}}bx$k1!5L+HhXxZJR%fh}$-7Js|GY5Z#!r#`L2xKN@kL>(p8YqpkuloNsq{cKhr>wwb7U@ zd1&84Wz!?HZ%&yh2^RaFp4`KF>}L+o!YYzrh-BOD>7Z;=7@kQ$;l-WpSoFan`MdM5 z%0!&xkKe=P*vOX06+IT_n3j8~mYItDCvTwot!Gs{Sq^YSn=ds+|W z@;Qt14BP_cxXa=!7t6Xg>Y1u5=-*}Q@426cOARKQE782zrs^|-Lk`u7qHI7<+R8Xy+5Ji!lZ|^Deg-`)Pz02C= zN=w<;-#uLM-N|6KoD*2^9}%BEoY0f)1fS4{H)9>98QnVbju0H{w=PG*Ar#?Ds(s!$ z6-)_+JN2Aud7oOxBT{;-a!p82C^vV%;V#2Npu+}6rV>}91Mek-PcB0xzXko3&ei-r z&XzcCm1_!p#BQEv`N9SH#vF~sJ~YlfdPWp?N!;rloM8xYr$;wFk8}NV>&OCb%L)-u&$_ejOP%sMQZRk%)+ib%ehlRyRZF~BmstHt z7%=)lbSip*WeI&;LSbEkAQyF&x2taa>-fj}C9bA?F>Nh)F9?z(Z3JIug`U;j_fD`1uXAt3M~%n!(dXVgxX@6`yjfWAUzzg|vQSqKjmB}$dD#6jCxzFd zL1S3Ae=e=t%R*di?;H=p{>r|(aeZ|5+Hqb4?zn_wx_nf}Nz~!SJlycx@!p9nO=+vj zq{MjeRQ=|aSoN8JazI*l$4O`r-;u9)Al&_;>kU&!!;Cs*Yi_r{(Q0@&Vy!T7oljf% zW`h&xlO$xqjsYl)A^bQ`?fdvi!7n3m#F7N++g7D@2~{XMo#*B}eC9=?50)H4oTB+Y z(lU?j9yf&otT@6SJKZntq~rOLCg}|H5Q%^m4yTrXGFfgV)kbAXrN$5xgF@(5rrt8* z--yB2bYp4h5!5LeBc~i8HK;D{tn3)(r;l+AKO=%Os6M4imsyK0L}cPIB_2K>AZw)Jm+8N)Du45@HAA7~%@;!Y z!1pmb+I);6rzCKuJQt#h%A)Yix3w zXm7N>z3CoFJb4>k#fTU5YqF{Pr%Sa2-BnrgI7yNMsC~;8nG&A&dC3^+{bEBmu^aS$ zadCr)W*N-hF)~`khNAGlm&!japk+=XOLvWno_3S(5_46`c(dDMEP9G!1mQAq{wTnO z2FF%H@XR@jsLWdNO#9M)<0a5+XEsX&6;h5hAuIBr!{tX^jtl=T)egzhf;pMg{J2UL z1S1zg9>$`)Eo1i0m1Pbc`aOhv)=%~C>{{`Br$O1Tatc3X^mColrt{$=Y?-@e(lV2OE%9DFtW_2a`P-dYCOb+iCN{E2Z>QHgXFrQFvn8;$8!^iXz&kOD>Ku> z+))8bx`Oi`X|XwRb-gK((}aMfA|X$l*|5^m4&#cU{2g$EJIb(-_ny5evUlp2I4jvJ z(g#IDU#bZSh~!Pm%kwDlwAmcVd)Q&NZ1)ofob}hx6QO|Esn;j0FEL3Y{`V|EqMo7{ z_}I%acK6pEHP(hluSLJ(c6uH(e?VAH!KDwUt?D8j}a3o7PC*KBS z$+gi$TU zOnL-WJB zA%>&+Hqv&pw-)>iqRnPDFd#niT|>VRrfLL%z*K5H5%D_cOUw_d;EUvw8Pc3GEBoJR*W4xM3r3(Ea1AG{e_Lo!I5jFk2h2hf`ukbf)-7a+WAXue3vD5~W9 z6=Z1!ldyZMSm8dzfAWX;FEuDf13g@hG_$Yj_pZh{?VYD6s2XTlcoDd^mxy48RtubN zq|_~Yp#32-MBIGT*wFILO9<=N-P8XO!m9_{3TQ9d#4B2}>~0xfY}x-Y9 zCA)@{eZQ|6$?xuzJlvi6)r`IdYwp9v>+1Mb6wa9E9warjsr80V(QXX+GPU~U+fb!V zQiVQ54E_Z2VZ36|7B=$Nqr0CoXnN$fQ|OLNlEKM&?-tf?A30(Q;x#$0w}wwVI_USR z-d1v34E2Z->O(}NZ#ZyHM|qVkeg3^o`}r~0p;}flMPPR51&Z49>$eMy|kFk1OlEBhkL2th)WO$hw4R zC4#M{oqH4A=1@dUOE^XdxK$Cr4$ZaP;&QQX@ZeMMXPt4RZA0vx9nLf2I1xmhPxEyL z&6R@Tiq>DM)T6vpGPG=IQ#$k%lIem>ShYOrDU&{NalnXHLNzmtkiyq)-)XFwtsU^$ z^CH2qCkcXUJ7u6#5@%2TvpzwZO1SlEQ_Z;E=vEax$i@ z$E1-`Zu_0~!Evkdx1gV0@U}bytH(R+JZCZ*v{U`N#$x}Jcp9*w6yf$$RB(}XyMX?g z;GbAeDUT*(z9*1~>Mec*LH6~P-=P$I!{-fe+vaE0p{{x601YOt2<(DslM@mq^M3zR zQBDYA`C#JL?n~@H|E9sKrPKOSVbZ_B+a_==j$;nF^H;gC_DK zhD9eNNFPmq1$?OZ>T@i|0Xq#V;`u;F7Fi8yY1j|V9(l>(y%pRg+#h-MUBhACc$ZBB z7OmOlM6F&deuiLrq$kaa{gcMETR1au3Fzupt`)6aeNmacZJ%cmsNda#9@A3^Tke9q*kUuuZJ z$OQ2wHOe6}h7*1S15`yH#I13D8tIo8g@}{C-2xG7nJ)^y+STwEmdxHW)y#7xVt+43%=JanO%h6636D8Yg`$pC2ftsG&P&5;SmZ;86I>5J zt*N4ZRaxEdI^v2s=fKwW?N8)=-ao>pX4<)hLg7+9wk+7B|^XE=m%f1!_p!Pcy~oO_{GWvXPd>)h5xb0igaD$*ONQ1jckmQDd~-D+~6vv zMU}8oC7k!>&L?8C-ht95I7|9m2Xu)60fV_uJmX#4oNcq$e&3mH z9&-@rBjWe1b8$Q5_tElNAwqYG$u_rP48hRV@;v6Cx|!teq@fT|r@4O1r9Ik)^m~J9`Bp95xl{&OTN#j=dk|tzaLt}2`{UP2ftw>c zH18LEcoGjibSVan^J`7NE}=a^M0l1TZpGys2^^ZZrE{8NQN_U2VSjDN0e_MhM{ zTn5eY5~Ks-8^)quC_uOE%_FugWh4@bU99~#?HpsnU%)RoCh@H`Z`|oaOln6?Xea`6 zn$%h@|BibAS;Tj;_1XIK!`i&u-&8`{IbnG3%{kP$?5bH@&e;Q~?%- z@Wyijf6BRS`yTREc^{0IFKltJC6>hVcHI)f@2d7V$!DKmvz%VIsMhXpwb)Cq<{L`w z9KPkLshB(Q*q}`!hyK~7wV?qq-wE}}c|j0E(8Ov_NNP6C8N%#pZ=eanGu>~Nu;0@H zah|Xzxo&BpIrL4DUtjer$ct_Zr+t>ECU&G^lN)!^ENx$cji9ZG{xKhV?j1aQa5CnA z$X^t$dUIr!IZ^dP7Yp`yzu@DqV-Go)>Zyk_a`CKdGY!tW$G$CRvK;;BoDjz*naB05 zyUOplnct8!XjU%cF2$d)!woMGKhdxLd{&PVm09caJ`gX=eB83#y)J?B6vqvv>PbVI z!j{$-!k3z}Ru*U7nQa|w2FAvU9%7NQIektWNR&zFI(&{S?<%fC8ae(eLi?mIbqf@^IFD2jGg)$1L~=BT>}MC4r$}p&-1(Ho(Bz~Z^kHO?9vuovOpuI?Ug_8}hX$+~dI2~pBdkYG{rja)5$`n}@++e}BZa!5DB(7Euk*=61B zVHC|TDH6o?r}?}FHez1{QNI=*s1p$x@0d|VmFp%F1_>PyD}|G1ktY#0>%3(7bQ+=* zr0K*He$_U<8>s+7xm@?C$2KXN4j*wlPf=#LYNRZfo=D=u?(~)l%y#&MNSJba7**r| zlRBWu=0}7j0Q%ICSe+W4M>j4Vu0;P0r4Zwh_gHs^LCD3|Tt%5R9(u&4W%_%!6c-_*XO+aex0$OWc|>}SNq?Bs|d&4i5G~>WfV7x zDlkF~!SLMmd=vAuNw(#T;#i(f=kjhpR zaw(u!xg1J79odUMVK$2ddnMaM5uW?|&c&kK`lK8#|Oue|+D`OX7O>K-;<0@C`=jF{=`*^id| zQTe|RZhYY@(^^stsl8}^21dCaNhfjCEIX*v7=2n(7GY%;N(GB}jF!(iLDBhnuC=hl zI;2jqjXejizY6EOAf+)&A&@u6A^*kSaP^~CWad_9SVU2jU)6X`$%5PuI8HCFb7CSP zdId%-E=zBA#86l|{qm-WlK24AtO)gM7@0H-TRBb3V-x3#GINx=jR=imne;tRaJyC11OOEN~62 zQLBr;f%4rArjfG*~BR;gyVX}mTQBv8o8ci>hUEBJh ze~3ou_^<%r?}N^$`So}dq|10&zdPIc`Z=qbQSK5fY2LG;5JrJPC@i%#9$<-mr2A49+d9mrA{nCW`nGWOeaLT531$se zph>e2c<`20o`!5mexj%ck1Wwadi7DvxD3tlIwv7A<3YO7J+M?8Jc!t;GE+AGcYeZ# zPJeWBPn0UY2MZC5S1TrE3fbwPL=nTY+YlPXFaK{4n(rhx^75f4?S>XMq18~nEB)=4 z$)4Q>D=`Tu7io+VLy>j}OuFA7P>i^FUU_{ZWZahI~htx~`VDJ+uSAfzNXPXU=B8n3Dc&LJB zGbaLh?kM*G!calyFI2&a^@|E}yhV@vgWk5mO+#zeXfGCjk&IR~Jwt&GncQH25p*PF z;fIZZ)P^N=KbN6*@9ITRQ>SUjao|G>|9^QJXw+d#*=JY$su|5=SaO8k(TCK!E@vqy ztAVN3kq=YO;euOb-53uyN_yz(eT#t+1UR=}J*uyBB5xG32nFDQd(1@Rm#rx7jesWV#fwGWYPolFM#L@|N9_Tpd8 z{5vkj2K>r%09#R94>d6+ieW#AUJ;F$P*W+HkYipU$`&%G@c&Rr`ib*+{7o3YNxSW7 zWY^pu>a>hPFh5x}Z(`9*V!xQg9a@U9&kF|c8by-_mkL!Lcx#uR>PNn#`2=Pv^ z%2}=pE5bP;YGFC2sWa!9N23Cy9Z$DEnkgb_1c#K|)~FY~yy^+Z6Zmc&C6Bns%0V%P zV?JIv^XzzeZFThDfdp{E<^T9_q}s-(-#l#ZWVAz{-GcKh9bmnj57rE70M52yCogI! zq>%l#L15b;0rJqt$l+;UfV`qs;3aMVsc`O@bH_m=riZN8;{SIzH=RSL-B0AX&#B2k z{O~=8YBn_KRSN5y#@nIggf*F7;4@0`cqM6^|Khud?5ZzoE{h5 z`*J;EcdCp)CLH%^uDpW-4-PrkTHUzB=3vqzLC2MB@M~6qOayX`^%U!h*Ct+7>p#Um zGhcB!%@dx#OrU?hGhIP4{``V=vEIJO^Kiw$bxeqbjV*nyKNtnW>!1mKdA{fEyscIH0!z5LA^_)7YN z>yrELw735TA0;>)wp}DA7oO!jD#3XVH%z5|Lf4Gii67L4sq&90Y&*m7cN>`3wodgA zIJtHO%Soh@ap<`9XbHHzJ};12N&oR~h?u5k)%WoErpVUs-}7L%wSQ-;9TVupW^%>7 zzxkifTP}Xp`@vy%^5;wSLQtFc$#(a^Cn4MSV2cY5GnJYCE8g(=o(O`5l;q?+u*?aP z`MjX{c~r3XB!q9932@X{2FVP2N(kFP|l;tIK{^U5&I4M zy}h!C^#}$Yzr8RDqZ%aNgQce2`Y+mFzafEFSF4Wx-e1A<>^u82BMSxD55`q1hk3up zV?O55m4jn=8sbV`CU!#^QRd!1xf2}ahAq-V@w{rAgUzc6LOA+NcB}2rDU7_BRG*(|txKNmFE)^1qI#_bW5gqtMBV@J`JV5&G$dtYcrE3@ z;c%21pEDbDd|I8klDS6bD+>AqYN5|Hn8>j-&*H&ykH(&@dSROm#M3>O`(oS?@ZEYU zT!@K5tKMN*QBRNh>~Fd_Ukl=(MHfIo3hV1a)1Gia>z|?wZK&JzB*uz0xK@+{prKt$mEs0l1v1eZY~d$LGgz+nlRoE(4e*lO6~k&D2i5e7~} zET01Q%zM1_GLG7Nflk6NW8sHwdUMX!);ptsD~o2g-R^Kan#;8i0&zHn%&!W~2$=|c zx@U)Ah%>culc!C~sc$Fn2F8}_p8GrtMg}$ew-`zE$ZEEV4(RhY(B5`MS+3bqqqD_b z5wFu)ClXJ~-Zz&`Ha51D++3sWaqf|gJ__TlkNOU#yFW`>PhesO0aw3I|IQ{{toSBO zPfzpb>1!7N5OVEkEz)p`m%2DyO|W0gjj_Py(yx!r&ZdP3+s$=wR90dGx1h>v`;nyJ)n+8-AC%;|K!Tju)k0ANsK(uLfgz%c&r_sAE))B+A* zBCA(aMAKLzSW0a|A8nIiim&VL7E&@)ov zezW<-!K$1grL9eV_U9L;9pZR^!F;hEUdYg4E!EabhvU<@T2-5^RCRkqX7Z0^=plhX z{tM>#6}k26-vQn2&DDljPnD)E2w4q(e)DB#q5$OX zf6Db6c;w@0O>Zubmz)RavfVT$6PG{;{WqiUSnIs`@>^ZqDfWuU2od4Ocw}_nRY7mI_fZpd_ zw?`{ZT^an2UbHBs^LRKoIF#gC`bf1kzkFO(=@hNX7R2bcYtGRV6pp_6Ho!V4+7>Mv z9RAaqud^iZTyn+$fx>dO%5XGWWa=>0FD)ZuP+(kKCWf4w<94Y(jz++7rB$QM^Cacr zdbGh+jU5;4cOG#tA=>)@aN>FH*WZP| zvFM9d0OMkf$pp`r1eg|iU3jhuMXI*PvIGL}{J@xh2w?EeC2P^@i>nUmL{ZGZa^KoD z5bE6-KlMR_VUzyf!?1wFf}Rj3lYD3ZMK_ntd3US#f9w-98slcOg--R5SgwsRXCL7B z|E7139g3wrFBZ+o{r=kWGZPB|`s9EL`1747bn7x(#WEk9mh3Kid-eKrrNjj6e@Yvv zjYJ@fAzdS#4cotQe>mZ)IO+G5I7H(9##Otz>hjaC7LWZ65H2cCJtS^G1;>6-dlw#- z1x~y!)ht)3a3SH3UurYO9zcwW2>>Hw7C&|;V zr)sJ&J$@Ya{ktFt-~9mI-kSMlW@bJ_6#)Ou9{a;Fygt6C1hml3Lb(`9F^@|4ah5}K z)JmK0$&{)jnS{sbj(Rvg-EhWJ^TF|PUOzto6s@=Ci+0P+KlBb?yYJ8z^u|;j%*K&0 z&dw^+js*LoZ+4jRoePhupcB3U9J8zVRZ50{C4P<=#aD;3y}I#lfEofBYHquNFWpuz z=cYvk1qG-BZBV+APt=#H=4c$A#{YgNQGo^nf>Z}!u3Pxoir1rucmoqV+=>-|t(}ZZ zTAuIC``zDOaOu=Qg3xftofhpIp8B5Kp%c)L)|wCKwD|}{;Cs(T8MSzDH!OS5bX<)& zTFrlZ3|N@pTVsErHlMRXUr$SxpMb+Csi>$#{n`e^(dhbgwf#0v=Wfo}BEII;i| z1AsXtBSUBIJlhq~a4a zo9Eq^i}qm&Xdy3J zz&6h>k2ez#O8^TiOz7G+SCUgw5@f)l278n1E?SFJgJTp8637Rx z)!pW$`HcKfl5~`rHSU?gi{q#OL(M8ZFjWm9lU;a7YECLC`P2FrV@`c@R>k7SN)%XU?TZo zH6*OcPh6==AJ|W``lHu|MZ^@u`Cs<^Xt={_Flw-%T1Gt_)Tot$q%A}+oo<`zSJ2Wc z%7x+|>}Qr|DT?<;tKYPh?!1N>ly2uU@y0716iYry_=^%q-td9=w)Jm>7e2(6R}40R zOC!A3IF5rJLMD1)p-aw|UhsKHr~9no z0MM4#Mikq_!)m&mXtO_V6KwT&FG&o3IUv9WW;8!QaKGV$sH8jaQE~~Cf&9xASiS4z zk?GwHTrz#0hZ5JPS?SSha01>4Vza1r#K5A5ZAxPzwvBDdHcHmr45hf%Y9Tb5I7Q~M z@_A8`J0<=@q`|YbtvRbI6+}fBkgObUrKs}T&GC_Q>2zj`xDJbpa@GLSzff5VrQ_>oSFG$&LNb$VNVL zZxRGvq8JC>3UR*GK6qOSXxBSSOV_PIBAZzr5%r&Ev&Q3CY}r8;x;NLe9oxU&8gmQ5 z0Pt7?T2@j|rvhTo330yb#B;nvis!De9|O_k&Qe=Z`TXh|8yfljuiZds902$qWua@} zx$OR1q70C2G7cUrtN}@-UuCKcHnUY@U#i=O0sAzt$pR#eEC{41E}L=B$R&)NYE=^G zSB8SPMhY#*b5Hl?QvmCA269cw%QLQcR0pzelq2v-KC21F@o{>e9j2dCQ{E4lprBv^ z=#e;ZwlIVpvYN2lw+g_U@3*~THRP!V}jEr*a7wc~U3t9;Pp=jT+<924H#k2Yrkg$a|--~(-TuL=c z%gdwn^N9i(rLBpMz(52rRNmIWoe8EEl^oG?6aw)z>x)TwhWVkP|EH5Pjfb-P|2VRB zyU7~LlCdvY$`aYLm7B;^UV;B2no;nHr-S%Lvo7VH;P>vgTq4cXerLVwO5Ib<_i?g&hiDlAM*+n4YNvE z{5n1F^nb6?)m6IsQbxvV{a@{?ESr|X5_}%~7`|`x^jm=^W>5KhJ2dYq6?c5W$y8G2 z#LgVWF8_mg48`WLZ`T>)kh{ zg@spER#w37{z!fKGN`|xpg`{6Y4l%qy`Si7{J6g;1o9wRmXWIuNCLeyo+>)nty?~1 zrw#2Njo!)*!Al(<{=O2E<{WF`X+7tw{1Bmvk$Dxjn?}deg zB(DeJr3G(iyBjJ~P*4bniS?~dR2Ti&yeuXrZD(iav^H9jm}JD`F3-{yfae`QV#r9I zn^VQz(Kam()7regG!TKfhxUu{pqXn9JNidMBg(wa*D=@VtO9TwNp^O2O!!RLJ{IR+ zRLx_;s;-yDU}Du+ioN~!M%|{M_*(Tdy2Z*|L@C$eI)-8mnsOX?D zMb^|5vZtpf^SBw(JVU{-i<%Y&_;O7E=dRQsLo0)#u3$cGTvCz~^jSko3k0St5*0{e zGB-Du&Ci7~41A@137{=@#IwdKjR9$N5<4%_XR`4_o|4e>b{y-2ee_ohWmlS?LYAKR zoAeqz%i=gJcKzf*`&@7gz1aF;fBq-woCBJK5cCTM9D4F zD0??LboX%=FR7k}#v}MjYCO}2RUKN0poJZcNsGKva91tg-X-@ zoKJQSonqPh(vqzqCZH;}x#<9`&ey&^_X>0G5~vMQpjZ0Y?$g-5b6kY!A;a!>qU8R7{X$&6Qa3(7z{q0-Cbnx0` zu5k3hBq3mJG?D$P(^lVA6a2Xd|J?+G^>rue9^B)h829PMS06tL0sdJ2Rae?_lDWKm zkMeIeTNk?P0qe71GoVFVOX(>7kKjBUwq`#^7Wo~gUADXyb||eBvd1SZ97oK-9YR7v zvrvAC3bYQ97}71{#f!SGt|D-*(eH39h~YNOa^K_MV=po@S1b7^zzM)K5s;A?@xy}= zp9TAqz#;z}lIDYcR#sNOtywin+6#*-S`pyTuJ|tM>}}3$4qr3-ql*=s_>?^Rq~Z8^ zz)er3nl)vj17u=iawse;Z0z@%tih1{Jl>zFRg47_@oEj#(0?sU|HZRswv3F7ieaQJ zgn1e!Mn?PK-DNw#PyhKRyGxRu?3tk_pnR4C$LiS(7!PP;yT{`?DL5WkGxrvF#-n#Jb3x3Ok+&_0$dYcZ!ksq5Um@}&!y6DbifV&u6 z`vZc$dij}umQu(lF$U{310oo_%eByzEJp;o@)2O}D?|1@2Yif;Uj~75)Vp`@;{i-A zB^(a(+8M?{&&lb7e8fqkRA&YtiPz7b(N}`m9Y9a0KL7;z8mKIrLxQk~$Q5iupd7K5 zIU{|1%1Qg+d4~B~)Ou!-_Dy=VcqB+UK~etz^sr%S}6g0+Nd zc4>Ay!q!?8u6ZQ}v`^%yh=xo?%^xNgbeI%h>*5>+qsxCI_9SO4gI_m%)+^#V zUjAgeOGW4Q>9kwl<8voj=TsUM-L|*pe%6w^>iGIzfx6asa=4ZaZaQnBX@A-Q(n3_U z%%3P>Y3Wn~fgoT5xuWUkAL2Zy)gf(bYx~;W{h95{{!GZJk~{~Ub;yPcpcnF1fL%KJ z`T{B{GlF--9EzoMg~N!r^9d+GgseRm;ZLK=z0Wrrlm&4j)n zCK{lh2MLLZiAz8m#dA#l%fpYMpEe9-rHymmfQ z?AHg)?Z^F4qlrLAQ&V$yWjI#GZPdWf@Y`LlHmKhz>FLfcp2o(;#TM1^)ox>V{{45c zI)TWetQ|u3@f*Y9pTN}+;f%6RX{bQ(5_;&4sV=5JYi%at7@U^l(cXrbbz_EkrIQrU zi{LJQ{M4&T=KgDeh+^A_D-(P8uu;iF2L{Ovlbi-Xf@AinEuKQ0FB)`y2 z$L}ia;~Q=?CNVKJ_#Wgtl6``U{= z<#e%M+>jn>N`ZJ}QxNpq(A@m2YPvY>X-H~XnzfO{jR<%dqM@*fipkvyYL2f$7SNOz z5ZZ`HbZ=v_3(6OE@km5e6m}PGXL7J|aZTUlX{?|hIout-{YoiB7R>za8&MIFxApb) z-KCR^VTZe zk6=hB$&Q$t?N(G%qqk4p?bg|B(b3zFhX9rW;Ch#v8(CajtR>iO#>30|_zV@@v$QlV zCntg4bO|b32;o2F|mzL_~PPW9+8zKpqSXL^L4#=(ZXUrxR! zrZb7N7gocUV)K%jPzQ+DQ{G=_L-(0-Yvq z)dR&;aRI^0YYyojxk;Ly*ty)_J`T z`!{8FUnseP78&;N*j||1WLb9%f_AzEVOj&+YkW-)b<}pcF)05%MR*Gh_5#bK6kdHf za=~SEI@~=DrOH0K6v#V@+P0C4?#HwQi$vL9@2oERn=*+)_JtOPM3(ILfRb08b{R^3Q?J$5wgd#_77~eU z4OC`u1K+W6Ew}V2<>dB5Ouk`}Sdy22?BV0{ovbd#L^U4PLQ!k->A(&<=ZG?|;`v$l zR+wm*EW2a9bLAp=(O!us7YDIzgotv<07c3E|Cp@->JF3myxK3-x!J3;%?L&ER7pk!+hMm{@x}atlB`xeOi0?ndX@DDWWE;9NQP1*S2r!6wzGE1HX|)#>K% z=q?El-h5JR9f^*^+u)~T#L4$tf)u>}B7A#G_+++!oZLE+H{DYmkHCC;Yx$cl!jYj} z;fz~ks;VGj)Hjlsxs8MV4#mrd{RL;|&}o6l3ZZavl>UwhwNJ~V>W-IHw{2!K`JB2f zZv4MfAh&bOY^BP$zETZY(2G)xlW|ZqQ!-j+B01kZWI+q?o7H`))hQZMP)}*S8099f z$s|GUCsphlj!$J$ zM)%mBefx?#rTf#6)8a&K;NMZ_TD*CmXXpbAy_tik_lJ}Lo1mqi=UPbQtbOoW`#}sY zZ~)^InP$Hhi(wwyaTZ(**-VWu7XpF6FebUJ+#o}lzl-oWt*h%5y5r+frPLXw$Uau` zP3`373!y;kbM-Cy9{sLEq6oz0A?~ri2SjajQ9Pqe=xnC!_G+3_GLHE za3JQ8y;bC7r2a#FjsNOeoKT``q=~9ezJcvZrV`_2U`R1xKFdLJ(i`^2bl>N0>lH=@ z1{cRTRrakMd~zHqMoUA3kEFtGtfSUpDo literal 0 HcmV?d00001 diff --git a/imgs/wrong-award.png b/imgs/wrong-award.png new file mode 100644 index 0000000000000000000000000000000000000000..2ed46ccd0b489ec03c8ef32a341c7572736a6b44 GIT binary patch literal 16921 zcma*P1yq#X+BZIkNJ)brjX^3QHMDdnUD6=k?a&}CsRGiS(%mHpNOyO4cYk}H=Q-y+ zXMOKKT#Kc^%suSsFHWF&~5C}Rh{0m`d*5d{Op@c|^2r4-x?94iADm&hF9FCvQpwmESGU2*vnj%Ops)Svre3qd<=U=S)_?9*U; zOz_v}Ge2PzDv=6_MQkAy`PT|i@Dio}?_Yg{!Mxtly?mM3e(mq?|2;O=8Fg5bJ1GH! zmnWIV7_q-^y>qg;?AY0kBPW6B*|W5%>$(gZ10$nSn?)fzdwY2)96Y>M$8jxjK|zG$ z^?sV?&wYxEnT`4qz9c78sGH9@uakY+n~{v5mJSRJefj3i5P`fOwveXpJ1gZ$3l3`8 zq@J70<5)gd4)d}6#ou4>^3^MXv>RLwxAKaH@>H2r3e=IB`x1G$oR3}i;D}HsI(+`E*A2Z zPISF5k<0yxjf;z`Fp%CCd+C|x95g8@sc$e{{7X>KGbX0+loU$H14P8m?rua%9-jDt z0l5x-Dk>@iW8*sRTx_AhV;j?DCtF(j1J88yiKTeuKZ;2@TY`lKFVzDrJ$;(CJ^od`# z?@`6R^6GaDWp(o>Oxo}BR0@a$JnHqYy$}#5iuDj7BpepH3(cRyc1bv`M9h1C`5=QK z+s+K(3ZX1&GuA9YZ5ANlR~eSmmAq#Y`j8oq>)rP;%%3lh*UPMCxy50cULLnsCHfth z+Bs-r=Eh=eg_+V)%m?qE|Ki#3En?Aj zAzYolSt^p1_CK;yipN~%Am@AN#d6AWlEpL_zm!`4xb|GwaYJdjUrF(wi`_jxS#t_B z36Qx((9-n9xyJ9xaqG~Dj@EyYSlL*V^VTyOvTC?-Z}~QqIGo>u$bAK3_D4dAmBQf{ zoy5D(r3xoiI;mCpNcd(mMe@s5qLaHD`pAM$2TB;k&Kph29+bXm78t-V7D5ZaPD2=a zO7p7@^#WPNRV?V3yq|4wnnQ5^^F-D?#oE;9#`(MmlSZHlTH=of{2p>D4`V3z#tcK2!hLiI@Ixb>*tHSLv`Ub_?QcK!o*yVXV8G$__{z|%lT9}Mtz=lN3-rb#7|$kL=0KG#^Yb@tkv#h4GJ12fg*R%7I~BIPQw z1i$xODJH~ysrqz@qTh`#GO(}jqU{`Pj{#H?d0}zA-!oo^(*gM{$NMnGdRcAEwP|!_ z&cc!@5|2AKQ6!gZBc-CxIa$4=(^0+tW}}r-gOGy;=QsEXrG<=Fm|~Y4RfR-xY{Ij4 z=S&`tIu37rz472Ahe$FyUxuhPjQMFjmrs=u@8LT#Wd`f zeuinu>s!6G*7T8?g54#U^NV|wl`T-GTE#z5 zk{7ku6KLhQzR#TGj6{IHbYeS_!)kx+%=x){in~EaD?&qAC=h)}UD%W^S2AL2KOy#! z^VkCm?nUzv0%N068Ck!U;T(nzZjUeY^J@dHV2!TJX=7@+w%+YiKF9F5L3rRz34MIq zgfT`Sa?^pI;7$>bp$;o{AtIZ@;=4|7>Bk6ElXXBGE9F7ITe}gz-0ZX=8Mg*fjwx$o z!B$jg-5-Jg?4|miG@+j8J1qM##Eqb!<3=&#%yg`mY0_m|_5uAje*4p;4SRTbD0&r! zkeok^QQFpz8@lL;d)=4|n|h}%mTeunu&@W8u$w%5K_S}V8A9yNr?>AB#IhWoQ^NT< zoGGEpZ-F_)wn~M&&};~weTDuc%sT&HX7?d3FPjtTFi3!%Oyza7-*46;;X zON9stzwzA5j#(0WHSnasRwYl$O+PlCC5%48c@lP*M;GOK_hQ$_h(Cv9|Ly%T2Gp+k zYWs3SaGU8OSvF$u*be2f*eMCxF861J4LotGRpjk0gJzo(&pAICKDnm5*J5wKo}%Br z_c>*fe_mJ;H2$N)WPWWU6P+qI&rx)^208b(<_vLkhGNu{)@55vsjAV2n}Yq%<+M_C zoSFKu*lq1IRZ=0g2etV?xXGgWAWRE0tba>Z;a|Ono<2%l_m^ z*jyqc^W{J;89g(R{@6AV*3HkUDodrjO6*ax+xh#H=tj)lbV?d@yE5i>l|)K8EgVF@ zY?k{||Iyh>*Cw+D9bp$J}dbUPj;D%{ra$ zgtM&Bk1Uu>G!VFRQ`q-P^}uul37_bC)IMlwk*}H!s9jV2nv6^nrhZMBR9T3hR+}2f zA&fy1I@kC#F$%L&T%K@4J=g6YyAe zqVS&fmEq9w|V6!(h z7=%X2rGU~?8BY+?J@1<$Hu5tB(1615W`bza6ApEOA$j?T9;vw&SMbV-77W*Zim1=-rG@;M6&- zf{$3ro-6+H=WKcDxRl2vxvQ7a(#rmN?pALxNVT`mtxWzNpY@np!`Cnx<+(;K@=xyO zS_BDC2lL;(8_;pb6d)D6-Qvu_8Goz9c@prhfFr#1S}Xq86^ja%s5g5}A$ zj{2+$a%i#3UPu#${V&$B*FW((nwbx_X2@g+5p-u*Fm7A*MwFNH#|5fTy1M9RTjcq! zQkPZJW!KYT9_W@+s%8`Hg~Z`CFq(({P|hDzOYav=MhnN*v#FI7DMq67XOHHR`d<3! z52lIkOqBR|c|icAgv1DV^3&1LLGYhESz2Cht#>|_kd-xF>xmT+`4Igzk=ya(*2qr) zpG6unj*m$#5i+uqrVH7x7S40XZ{?&?dCq+gRK`ZdK0wX)p04r!Lj}VLIbrd%@%)Fa{y~jdSAuD^ zpR1}I-Le-q*PIf(D!&3w1lUu2i%{tUM7zpAvJ= zFP~2di?~X?VI}FQu}22C5p|rn8>mEP)sQq(W{ib{gX8O)upI~68lmf9eg0v1Xh;H# z!m#_tUJ&i?mzlDJaxCkI_83!rdsS!pP+R;4SU|;M$1?WNgXO(>eb=p*k)D*kYE>By zEN< zM32sAVe?2NV}3c-C&mn*F7})zf8=4Ex=OpoCroWpv*v?ZIo6HRgb8k+Md=WcKH}gp z$VkK5s}R!&xVLyFNX3W{jUN_3?y^xooh_TJZ8-gvN|@-4frOSgZp*5J3%$!O%~%@m zytM!;U!Y^M8eu}q&Goa84fDMG@Phj)grHzb=7;XDP_gZ_; z_*Z%TDbmOz19_CE$mYe#rYa3fkUV7NBYC+;fWM5pF%NE3H>gHohkows_21Qy8<+O= z5H1+q!EN;4_6(i7Cv)jm2W=MMqmPUU7}}p`Upwv;QOk;7vR92Y-OWETpT2DWSYG`Y zW1t{hf0c`hksV;s>XyY@NX{H$KF$oHfBJY~mdUJf%sx{|7R~+XY)%l`iKl??(HryF zK_mW!^>AWlQoAyQ0S!*?SHS@*qbO9|W0TGOG+a2!%Jk2^UVG4)WJet~56KVY!?1v)vB@Zgr$#IUu#3lwk67si+~a zjA8xf7@3*-D=IT7!1NqN_OFuJKP|s+g_4=;KsWdx%P`MkqZWb|>5Nd}K<*UTRrOi3 z+Z(D3zfp5~%ABzdWq*u}MUCoMOxy$^1RgP(JOz-I(jJ{OYU!2%h_MmXozGZhoXkMyPl1`9R$IrCitQ*4?twi8 z4<;PINK`e8Jo$73BRSdiXhSe3=W7cU@hdPEr3gl-p_aVEe(=^5$+M}n^CXQJNt&15 z3IipT<&ES}8w z`%!yRsxs3W_eccs>H{u44&?m3ee}|Fr0IiRbkrC62fI+4B)2{l> z?JYv}?b-C^e3Jl#LAB5T)N&&KUts4;&o>?k)6NJNX<-o4{t@@ALFrrLJKrWGTqG7)O){aT~) z;HaA^A|j&IzMrpyp{U+l?~fL{d{vLEsuv6|goX3LUpk2AXJQ+q80xEFWw>Bs_bS&O ztHYyf56SY`UJJSo z1l`M{)mK`zkrNXWW@OL#`I9a#oFD+k2%DIggdR`qo~iHZME@;*8J8K-SY-5clXOWP z_ILkgXig3pF}R_YZav?*Q=PZ@b=!T7@obx{ShW0Qx$FMBq<*sh5zYG7D_d}gh&C=f zPBsR65_t%V3z++(a&)sEixO>~G`;-YnOcKgViv_JRD!%LNowpRUVi&z|KrG)=1~*xT8W&Rfsc zMsZk9L6~)$A(a-BLTYMHH#avkva)aq2v!SY(r^am3y}>|#6klGe%SD$y3^w9Xb%() zw_$lz$oLH^d{e0&V;q>y^CwmX`Xq0qO%C`gW7MTsQ1PzQMqoapAI$4U#`X1fUoU0-?1SZ-*F|l!fMCNtQB{;Q>&~?3g7lw z;0Y;Fdv*o4zrJLS$zq?!PnmKouQbOSl{Bg%SaM6KU81F>U04nmSi3k}#wR3Hb+H=D zS98RDkD>~ihuVC?rd{`BOX}mVtJ;20rff9$ZV+;I<`NFTY@430D`Z7o{NTZuGsFC%P@a3_+L=GFGWUCvJW2pd77l_8ZPSLc3CCtNP(M>J0aFseY1( zY@g_x&o6%aL6xCXm6q>RRGus@E;=TP2XbeRyQ2w^i^FyvJ*5G>wD9C+(via#dwpGL zabvQK#`CgU2W(-3%+Ia|-3{qLgH&P4HGuR~ts~lelER_#wNIcYy*}TkdGW%R&-F~n zSq3d2M^%Ot$xhGiJJ7y!2+{UHSe+5 zX8MCk$D^|aMV_QK2m8og{`Iqgfb;bGTk^K4-+{3Z!CxEuRq3^7Kghj>M!tiOI~~_4 zI)T#A1SsdJu;?~>aihKzk=~G<6Zb4Za~y@9%#kgOlO7!p)HRA$eDS^E-QXOVW%0{7 zPpItAYb30MZK`t6VT!Q9pM(fAHKY@r^Ui51=BzmfSkbN}$H^4kX4daAyD_J&sE<+NpJ>;qI{#-+%ON40f6S%kz*h64&Frw~csiDPuBU#<73_#UD zYHu4Kk3KnZ0Je&xh{!|8KQwOi@_ic4(94%L+)Yy9bgtL5D3+*dPjmR+9LNT~`}MPB zu*zD8+cB5>)ImW3S6-fw;yt_FibP?}8u1fG&5en%I+*od^)jXf2Z`tX^}Je*-AiE8 zJjfSfx1QrQ7VyFT8lmToQK$*lV9sHc;8b|d+MN{&wMgr-((=V|zkui5Zkciar!DDP z*nU`YvQDO@`_+kUPvvxty)kG2iQGT1*P{|qz0lC|jv{T_OhV%K?Hr#`5$EgFFF|<@ zWX*Rk_Vdfj%inSIUe!8o6LDC?EZe%caEA-rL3`uamn)~O(lx5A)@Pair~E4#k{4_h zPw)Q2Cv3DDhur7o%l8y-^po@7JW0=~_f>o=XMlf}Z1Bxq)&5@&jL+2ibz95f@MllJ z#WXV4AGa=K#arbbk|dul22gw~nJ0oEK2elH9 z)yXLtjx`)uJ?WW|xi$hN7yP3uj8cEc7MXIMacDn>t62e$PUVS|;;D~0o?RB4a zm(s)eKY|ZrGadR}ay#-<@#69la2HckQ_yCHN)5Z!o03f+efXH}M-Ovd=cQyf6W*f~ zPBl{bR-YtnDLY=BnErUB)&h2N@T`?Fd~HrwhGt}B&{q}r8UOM|dO=P7Jvq6*+;lhw zYWoZzq>TFdg!Lp>Oz8M72MfzLfTMKFCYc}mT<_HtNwwCRxRsB6jkV%~I;U-++m%x8 zycze$P5Wk-Yf}%J%Ei@Hsmb6oa*qqW<}K6;hfM`g|An#mlnkf+#ts2FLJ{`=^Y-;2 zE7GN$!b30qOa0OHGFJIS*IH;Kc4&m6pMHN5U;SY_$;9ru_TK)!ESShdB)qimWxFJe zy;K!P1ObeUzG=hC(|o?zjx9fJ!9(U>SzlM3`T^We$tiAMoAyb6+tCK56(hB_rF>R> zs6iqIm1gVD78aKi6Cko&++FVvs@oqd2!eg|Cx%6Ti#yrmcaN{M(#+eTJ2g(LgSzYF>@))d4&?9HjTNs5Y<^nE<6yaDu*19NAaMHZK zJ_I|BIN?gN?&hd_veGjC6#>ImB!4mT?O69fCSiNXy)gT!pyPJ%odXilquhPUZNJ3= z-E);Sgsa3T#eqGsbK{MYZP@%Jd3_qq90ypFt}J`OU$9T z(y$RE$I5*mxgLuk%P|j4u3#z^W-WSqMny*~RQ*}eFI_sG11z|#!m_}2#@9&Rt)!xe zUVj(|GM+}_r}jMwE8$Fa!4h%Y*~&^0VzUAzSLgm}+%ZuY#X%jd+(OwjzH~a(9&4g( zcZMLKh(clzyTvkrxPwYWYgk>_1ufTblrCvBg`t34k?PH4CU(->+EkSOugU15e#(VV zNC=hcudjJC*itCA{B~_ryse%1UdP(DzEK|#|CI$mq2dMR`y!6RR4kncpf!t!3AM_Z z6-K*L6&7>#u{Sqv+Afrw%KC9TTZ%55uSWEed9n!(yTtPnP!=fvV;r(am_8C_2!d zw%HO)M20*frSzeG%U5cp8N?KlBjDo* zR0FSm|75_Vpr9ak-C+T7gwCFx7i?^i&CShb4f5xEvw7uTUc7j5uv6Cm0Go`gx2&JP zJ3}(!e+vbaDp?|CNaGzh-IuJTn~l!R+WKP4*yP&8WTARBH3bJ?2t|S~cCC9a~jRT0BHTVsSdqrItzfkk@XPsg$`nl?b91!tdXQ zEFVr5wy@&>buaIB`#Yc%aqGjt0`0y-Yd}^QFhzflxx2h8)OCgyqF9 zEG$UT@G&q1gMXNjX*lsW(2>)3u~2uYT!%lR^1X&S7Htm83aow;Cr?!^(iRaB835n{ zz?IJRWKWs-MtA3xZ{ib;?yeQ{Zp~f@78At?#qB|lNudKJ?#u0=CIwth2b7=;4>b-# zHWTLoSf*8D&bg9L~*u_&cQt#e*9ulEHc|{5O3)oCq z((&yeJrc{T_W-0&i~&Or+pE@fyq_)6N5zOmP8^u$V0MOGqFENs^kYtvoV}VLq1=T{ycT zR$_bQvR(z8&zUUTG;+}HfQm3tqW_fV(~fiU`Po@xMyg0_R@u;^6Ykazy1#~pkgW>o z>Fs?WD_n)7`6betdA|4X?J4=n+6$q;IIvJH0FMNB5ZcXH7qYTq05-d@ zo!uLd#)xX6%H99tac~@96B{oTc=hLJ3w(or)YpFsh#+jqzWBdO?yIU@6#HZgYLEy9ShqkU z0fh{S^3|&lz`nl!_^}q#Dut3w#)aawH8I*N2nfUKNI@Ec*H!NI2Bp(gs{VTAM7 zQ>a%7vs#&)hC<4>*akF7HfEVnQcvJ=)SQlKs1@rXe5zA62S~jSY$ z2W!+!hJ7L9D`X`ISfyZT+HMzAy)o`1g;OIy_yL$)>1JwL z0f-A+R$N4c8E}(k;#80O+jCZv0m`u=oqn*A;ETn~(QQ$k`;vCT;%joi-45abmhY43 z8lE56OStyAq02y8TmPAzv;^QUaDfs-LLQU5pU7XGY}$8v?@X2j930rRw6rizviJqR zr10bSp@iZe*`+AL)a?Hn7(*C{o(-l7BkzGY6E}LP^RZE3^%7dgGQ0U$vF)|>YHYdf&<9!YH`Gg5jW0FIRg*!W`#{)Eqn$l6CG zB&(~dGoJUizuVe?6eVG0RhaIs59BX+B#eYa!>|cRU%<;lh+#FBDInh7{lo*_z&`hv zp;CNA;87Kta3B2gAe>1re5d7SQ(v3sR{DgHMm1l2b~2A_?|%gN`hj*bb@7xzP%5r*f@GDRM5GziJf)YyLs4zAm< z1)8B*0u^YnJv}|d`+q5LA1;TYn}R*=t%;831d;r!dAM8mvF1$#FCdG31kPII zj~{OwHss)FA}uY=j4TBp%z7aGMpg11G$U5<7gjr*{Ax(SUolD@_YA7NTI=eMju!5+ z9og8Pjg&)KlmZ(<;C55?F*$F{PsQvZP`NtZl&0AZAU6d7aN0w7JJ~d-8YX&~u)V7C zqa3TNJ5@RZDBo0?Z9iKM*W#_Y*K%+}gBj`kmnCyR5C>6Q_wMq1gGoSa)+u0_UGy+7 zRZ>xD|FhM5dS4rY?A*_@Ry3TP(HR*pj*gEnO~v!&)5S*Bpz<&WnI{+Q;?7zb40GQQ z<>Wta&ESn@A)b(hXy4Oa#l-`UJq;b5_U`H($Q^)O+PE*FP<0fbPTOMz^=DJ&nx7^O zU(nDDXGxQMkBHcus>s6+bCHOS*1NkDR4PKqnZG+KzW}Cj%Hxd*49Ievj^5rC#nm>G z91CYklNwg$%baiHwa;p?TM(h6AO7h!&Y*4r3`z&@HefGh0xi!mQFg@7$2FCb;&%6u z!&FTPQ*GLV<1(xPny{qlPc}^Dp$?kTIbm7=sh<$$4S)z$(-o;}_FhgUSzdi8cA6gO zp&*M29@&7@bXt1)Wc4B8)hT*-=D7u89ih`?K_?1=W!wf#N3=-O|8mQI<3@4g1RrV# z8Lc@Qp=xKZdMiV{wj;i@?|n^)2;OBNr3KZd&4 zKsn44jn^qMAA4yCj5vgxFAnTDR)as-?V%(cKuMRAV)3}S0M}<^0Xe=+x*Yjs`DiRr z>kB5A&FvKYt=ca+s4$^;i4y@r;kV4~`ksP*RfP_ZGx0S&+K}c1Q3eM<3#NV_vv9%B z%^gS1=OU-6`5rt)Ta;T0zs#1x#P?6 z5S}3uMUfAeTr?3mq1pF|CZrczi^LTgNx%<#Bm@M1LPG6}%MpW`gDH~N12nB9^k44{pdQ1^aCD2bSZtLIo-e*~I z>|AX#2iv?xMN7f^?gr7}#*CIuXx5H1*V#+M4xNe^laBN>aE!RYopohB)f4J%W-hH? z2%|}G?d9B-TecRa+54?oi(NV-56s2(`5<7+Xbt*dV+79R=E}YqrWC+}+^&j;^Nh455>ijHKr-k) zU}?p0*;9LXcn}JF5dO3RVKWV~9e3yvXirmR^kHmBNh2L~#V!vO0of{$m9-&-&d46#pd9t}>syC%_FYkcgi%pZ2`AI_hK!JE z(@3?{A9RY#eM>}Own`2~v=zfMyhVKYUEta##R+PLX?LT?9BbK%fBS4dIYJnM=&sbC>t;h11_OG&<6xwcjkz zD0F~dP!>~X=AewPu9PrcU=Ob9EFn32w=)S6C{%s2XaNBO-Sa}$vnG5StSGB`>8*a) zOTh3Ye;ZE?G%2%%sGNCz-%{5ap6?+0|FzuK$(tfv_!r%Va}7QQm2XEx%Ob)_<1Ae9 znMn`VyUxWLK}#|74CmMf*4#~^-?eWTia{mPK<(Fx1VYrs#w1%?@p1@)dtqSqE1rR$_KfcP zSlf@}*ups-cE#ElM_5nKdmtVHu*WDx_wnP$>b=_S4<#Rw%*PAcz}XM4Y3ruMyW8z` zw&k$A(0J+l9$-c0fnoV9jCEMQ`_1`eV~YxCN^`3@oCNzs45 zmc^13xR0cKE|EF3=83xi+#YPChr{()G&HoCghCewQ&bm8(ieL|vs@TJ(W`roO7;6? zdimJYEEV8r&TFy8aB~oTs-dQ)ChRP9wL2O(+QJqV7E!kV#C{16N7n62-~vEv4C*s$ zl??(!?bpf5-x3A)5(MOu%CVX{OD^Udj0?h@f0m9C$o|jylfSb=^y|lGXN6~XR!pP- z1p~)6n&1738FWwj{_N~*R@j~<5NH`)@*^W7iPupuFkZ5m3##Ioo9 zaMW6&APh!VHVRTv|3=6Ex_oe8U=FyvPZR!#TkM@ zI$&enE-IX;CWABt(YZiaZBH31I+ciYO~qeE8gRykDlIkOII?-mr4EpV|8!xu`eK?S z?k^D6yp1WDNZ7AjMtWhX_3_n!s|bxe1qrJ{t-8{WZ9(+YeC|E|jEoK^-`}X-l1aT| zPIAK`m~89q1ecPMrD0kvD)@OC98Y}8TksA1c4L)jBK z9^-iTGDn85*(my#JNTVwAv7T)BK#xB+m{EoIGr$k^+W?{XR{4uTF=;OIg~*siA5W4 zaBhKhFC1Xj=Vx@l$r>s0KG7>6k^%8Ca<^Sl0FiI ziW{eU3nMVM&jgY?lXZ1>_kQuiZmGzyflTG6IBkzBx!v%;*n3bwm4T!=_9)VO;0aOH zOemVAnyCPM*zGxkgqZFp*lQ&Ao!wFa&DbLs8uF?kf_}a=JaO1UP8ni4P!k-?#R8P- z_45_+PvVmndonM4vB?X-`&Oq(r-jQ*h>4{>Blo`sdoM}IMHv;;h$n#Sqfq6Ff`E!p zpxIx?OVZSVCj0;ND{#Q7jt3l{3cM07g!VZdb<)g|EqecV;s1x)T)X|(L936hXFxh~ zgrUgdJbk*kheEjWuhUb1FRy<((`rP!?O#W>s&e6{wBDubgzJwNYSkb2@x)|xZVaXa z9m`we`2XiIt7MHgaao=4LIC=xEdS*Tu!CQHDE0z^5n!dx3!jmTr)Q64w*eM;rClEb z#Gy!qn>|?5^JmXmp7+htB)hc$`%O-25TJda3IQF*ak@qWqzi#AMM+8NRb37BLcik~ zRtLk|FScKoiDNSr0vkGUE{IE~5+v>5rq#|T9uQ!8!NKuFM@I*uQmEMpt_dt3peM#R zx?hi}Ridx*n4fNqzS5`+dHL?g!v6j~&N}7-@DYuH*+=9rcz<^r3lucDR{Ly{5|AQy(n;98g|PfroX{6~$07re363 zqrjw5*<<+>fT9AzS07SzoEDJ^D#pO6Ef>INz#HeCmN6QPdWowHU3V+S9o*dN$JDn= zOW$b8$t~clGcqu|>u7J^0*-D$g<~HO81~2Pt3Zyz{o+9H_MjDur&4P}({jF13)oB= z@mW8yNTDhB2LS@rywhOcIygJmJYS!*=lv2bz>ud%oW z*Yh`kY(T`qNH;4j{QUfOrmMmMQ$*0Mnm#-|J&mz9j-v(xRZ>!tQ&*SL)lJdp*Mh6( zn$GZB1!f=4bFq}jG$4~D@VmzWmL6@iJ)DhI$@-25wl@MC#_Ujqq< zhK}xMU#S)?MYHRELkAG~zbJH-^y2l+66(19g8N|6(S-0*Z*Tv(#l%Eu35mdETL}r2 z08BDF{j@G%VQ{&e(8|lpudJ?u{`K(f-+9H3ZORuDN+qA-i~kznm2F0(-{jNdB#9Ra3>pHCInhZ$6U?&9p`6Cg|1v3UW z2#@*@6K^?bflmh$88%)!^^YC>Tq9d1k+i>No0l5QE-C5z>$6=3%X44*=(xBpprbhh z73%Ql=p(!xi;9k3%&>1UV9Kfh@&)t_#jN+gIy$n4?4^E6c@9>0fqVce3d+HRl|OL* z;2jn`p`)c>rXdgn0LL7aH`({NVSpci2U!dbSI&V|3Oed!g?V(hy;4A3-)Nf~kp3nt zI11~Jq+sHvB?;f@BXKAt5}g(7Eu-2Vr~Y4G3C*!;f}$b_eI@Fy}%Vi;cz25JNtM-KOAA~ z(s}6%jnkqZA@9-*5;8Je`X=g z%i}BH%Lltv^AE@z#x#1jA)U8w06`SiA>b={S9(;HvFQZNYTlqrkoe{zzKIS)hH@$2K$&MDy-7 zN_W3Lg9pjL{;o=_LqdP@H6}*F!-F4e-1iC4Z(y`Z=bEMk&OoxAXmI8H+hZ9j(HD<4 z(g0x+fX~A2VgF=Ryd1C1Zm&*(;}J=xxG`R&lW15c*I1VL29hP4+=tFozpxRuy=Tw) z@i&V2bTWt;fIS5s5MIt?jrqx6C!0^%w!n!n(8mGY_4YIXF#g0M2E=k3DeCIr%Jigr`TQ$tLs90KyC8$|K-6l$Z`vgT4uJc-^n7n1SwS z)D!co>F$)NgH+kN@sb(@$vXP`!%3{`zX6WgT>Fe02=ic;;Z_egoeW05N90@&7(f60 zjXfxbC}?O)bFTZDpz~Sr6s6gkj6{$IwfBO=XS`MI&#r=8aP|Th8@oBLs8LE%64idK zhYIXs7X5aJ&Bg$gKL$xVSXq*yqDY_$&NvK9J8X}IrlmcDCmt4juwvdAqJfnI0i!B% z$fM`uYfuOSE`c8iFCMg$SbzQgy#>zYot&!mr2>Jtd;I5lIMA=VulJk!0iEdurAbm! zQV%ryurDW|yl2jeRQt~4;x5qu<8~65yr5vF0=@O&!-vdPGf=Pumz<>KFIH}iiUskQ(#@``qOQfy{mj{=(>I`s&ofHpv{eizM{39Qp$HgJ-Dg=x+OEb=rk*%ucV zUlS91w?^|A_$Y{oK4fYw=YyqH>#*4(aDOQaY*sGd4*+uzX69HI8HwL`f9DDc8o1x~ z>FMd`syo1s!^a%V!64(t_j28<2>_+l& zwFsl{*NgoqkImxpICz{{z5XjQGm1+0nxWc6)#ddTGZyvj`DNiW3r$S|4fdAV8A}J~(QYfVB{eJ*w CI<0>I literal 0 HcmV?d00001 diff --git a/imgs/wrong-loss.png b/imgs/wrong-loss.png new file mode 100644 index 0000000000000000000000000000000000000000..afd22b36277358368c24d049a9b021bb4d3a2a0d GIT binary patch literal 19203 zcmb5W1y~%9)d34uTeZoz{GcL)}OYaqD0yE70-2p-%$NP@cs2oebHE`tPj*I~Yz z{Px@Z@7~>e_s;Y5z;yT2R9Dq|Ug>i>L`gvk<1x`=BqSsZ>9-OpNJ#gR!G?i~4E8Lj z5Tt@X51qxN)lk992i4>=_>AW8R?`^?3H=#jyEnSvcZ-Dd0!dmzRLvu8cfr#~ZQ|8<%Pc~A4+Ozs>E9;E9*bp(tQ5zEt+@KQ|AMfhSxj+?T{2=7OMZ(DjYvxGu?|V%+GZj^?>W!@I8&nF3-*02E z#Za-?V@!gu#Dc=92|32*sE*{`CHnb(P)t*!S4PBM@8cGb*igKKc(S zOfKQVFO%Tvt0iOP@Hu7KRoHRFK68WLxPK5Wj+Ke(pD+la2(pN!PG&hI<9pcg=0jzG z0Q-X4W%%}6*lJ$1)O=Y#sOKrrC?q;#sK+$-RSvxC zXH76=^E@^wZMohaex#-K#9w9$CGz=ci*B|zGer<@hoppTS0z&dtN!4Fr-DCYXkK&=bqJn>g;a6FVP#zy2zobXgMUzcT zqBhoIr&m(`R9pO|IRi^9t%s7b=Q$o;Oh$%+mKKp)Q@V64ZFFWP)FxFvm7C3VTMda; zA?^2MiS~%r1BaDPv>$q`XJ=>Adu~QXMq>CjTiBbpw%5jK-Ps_j%nv_KFy{IUe*O4-n+jgaP&Mvp5CBxolmALcQua8XX zx=ulbr*h>pat%-9HXue$zx7l>V`|vZCJIu9h7{bX5$2h`3A3|WWIl(YZz6~!wY0Q~ zY)_7lfA{r0Fc`^^tk)@3Xw~zSq(AqANxL*y{3iQE{MnvYI+I0ENk_8M(LQ-D=XQn2S{3sZ`@Tmj9dyb z8K3L0Xe2IbC`Mm4vcwn%{*Gk*`(9>hLr6%NJ}W|bZBkiPMbE;L|Mly`sP2wW7{tGO zdMs-PE{|3<>+DDk_-~{lNkUW}C-(gUb8v5rr^v6YwjdvK7JjxKm>tf0zfhJC+rhh=4D zB}oJ#jKpC+_-Csi)2!{oBa4z`Zd;-UD44s^_3{WMqWteRHals`4|(0MAn{7V_ZW_2~-NoDC*=f8fE|{2#X#2>Ln=-CD7d02kn2M9wS{b zEd{3jkV-mVfSNj+24R?t02>1Pukpn`XHoaKJfJ}!&<9|^q|aiqYKiuaf&`v{uD?W_ z1tF*ke+AIN3~{2S7UDzzG^7Z)lu!aEh#Oe`1g4?wh)$r&#K`d|HQ&5G5dPcS zN8a@h4jEs*H24*Y`##}UI3Y)pkhfb^D-S1UIhcU+-5GJPx=uER=(xCW{b4s3Cv(ud zgw^h-+_;sBZZax<{zh}CKO=_kAA_Nmd@M1E`p<9K6HF_7uAKaCSIJjh_#5DNH$6Q) z*%0_$z`tO?TJy!C@mg>Eyzj+=N3&i6i*9ea`(jU)XkcM!X_wu>Rb3u3rX-{it%OVF z8yN&KTM}Tl7@3%;g@n?pt2uYw1Y&9BDMdtDXSji-8f}k%Ly}A5jV{ry%c(KzOJIIN z@XB8_5cwV!IeF9o-lsaQS9ATb-(DVEP2mBs#l>bOteXQi^hD5&KYe$$rf9$xEXvOz zA=!~aU4LV`Nin`|W>Z^5 zP6t1;PT*k}bIe;GUHqO3QIqa}-rXB3Bqd@Tc}e0Dc@mO)`})AYqIHh^>0q3;x3>W- zcW=2k-Cb?Oe))p*QxaddbFtYwkT!XKUdPGV`9V})Z*SxCvc9#)E%vQUR&|i}5Efy3 zcMFbMREqzMEBbxY?Ck9PH4ur@9usqORUI8UX=yY7$QZ=jUt(j&Y*LR_yQ}OL_>s8n z=70Z=rc#z+GwUY^4Grb>Jf_wwOB@ouDW35U$oPtE(s3tNJ!$BPm?uu`k(iLs(3MGT zd(-9ik6>9K1!V%B`4~C95XP&1>h2! zIOmmt(MW)g18SA%43y3xKo1;xPcb5ogRBMSMIiAiM^1{ zpQDElo7TnkgP0*k&RzDLhHxtpgc0C-gUR>(6B2-Rzm3^)V{^n>(C#%ALk*x#wkwEZ zcQ$1(L0JCV7_^TjiPaz`xG&94kxjx*0o)1j;uh2euirhI9mCpx3nGkS>Yktv9gnoc z^923^(R=9_w0rSPIP4#>?t??0>?d0j{0J#J`4nR0Uj7~hBXtinj5a}sY-A+5-U}R* z(a;7js4zpL@=euSQdkYJLnM%{$nX2H+OON%TOhqdztEB@|Q&WUt z>Of#;K5LBnTU&?PvTi+~;m^)`0KJ*|jINH?1P^~cVA8A%x>)p%3PgFzJ!iHzThrOq zRq3*&Vm6TSt2dr86$ZQ7$lS;YW7+O0pWApF-SAHn)XDAbVxwbY(z3E0c6A)U!j4Z) zQf;d&$7u5v(jWiq48fUcbY;}CMiRbUdZ41Jx&>{8CXI~Yk)>{uYP#iHRsbb0otY8gz8M!*yqp4TQb_Zmma$9ZykeJ+IahfkRasemJ&z zi^INPTKFoMG6-w=8MZVc;L)~kj{k^`Z={JgmM>4m$QYKW=M}QMYvbhPlqBrS50G@V zv}vD`g(dRpWFuH$_xzDv2a~gD5Y|R1za|S0i|k{UReH5iWX9xEq6K z9xGx~ZT8J!`-uwER5@njRr)K#uK>M}AiNQH%k2eghCI4BRaa5B~(fK3!%0 z^yuiQKT{-gd|XZV?$TJjR41f+wau>1xsSQdVfiDzo2=XdLr=9y_2kREcG3s{wx1O+ z3aRvha>&q!++iuCKj_C>_~)J55d?2M zE|NglhZo7d`3z44wxx)ObM0HM)-6$%-I{0eR|mga;7yMxn~3{mlyC@Uq%*Dgn{0y&HoXVm`%R}^?^G3k=Asooq0 zi`)i;hCZg1OF~Kt!XYPzuHj!eBZ82B01idQfcZayko#r2dU}JbkSp2s!F1wHj>oh- zJc;x3^FLQBD@zyfX4afsz4UF9;p74?{wXXic2X`hwHeg^L--NgXA0(vhL-kIzylPg z4h$Y7hs#65()yK9g=T|SGcz;K@$pqvR6caC8iL&8&!0b>b7r@fN5$H8nEnyOJnT+? z-o~knPfk{XB+{;Ni*``p;Kx`bjfv69PrKmWPzNc107Cg4%*nvTf#dmRt;9TbI&}}R zadCf@)GhY5e?+ff3bP!`kB*Q3CCl0@;pWE8$Hym^DV%QFm*6<1>yC|&-+g;^a_{n@ z6+RG6CH20>3b#nT$&tNdB zF|o19f}ZSCI?fnw-ocsq@&Goi9T@FJ+7l*BI7;D^7`a3l-_O~Fxam3tmh&g&{h*vS<^gKU?;Lv?yZ>b7{h^<%1I7qA~c>qvS09VNa_2EGDq%V=RASdU3 za7Wu$>DYRZw}}x#H6>|ibKAmS#eyOZFG_W)Nv++&?CueWBMJGOOse98>g=Ip$wg#R zl!(;DG18K!=XRZ^746y^^5KXs6%4&A#KfFRKW5~eok<0RqO&1uf%;@zRq;%XWaCp1 zwGy{O;$Ohu#7=L_4CfWd=bot1zd>`qLDmuiJ3fo&_x9h z9(KenU~VOEijN}Z1_nG=Krabua2^e~#v9-+g2V4A>3tB^!~Yw&eMKBUcD<9e2H&m) z9tSf3+YFI-ne#}qFE7b)QT5A&b&!UD&Zq?+(BWA9FAFmF%e~I5KtUyJz-%=YdP@t^ z6pU`|%~z&X$u~W5@qe8L>bK7pJs|i79>#Mi0Oft92^y%ykbyug6T8)IPs_;IShLZE zzRGOC2;^Z%B!V7aKrnGwqz?-vhiytR>9>&dRkj~-^LHnQCQN|z*t`Mw`;Q+#ek~}7 zO-T5(U}rx1Rr=4y2G5)sh#ch7`EmWhI;jM{uX+;fMnrX9XWNoiRt&&vfa=YsWnGs@ zr~KCqh;Y}u?(@sUh6TGc1@onfu`QFSQe9g+99&#UIk_hj6BG3dcA(0DH$AxQu;kVh z*rEU`AD*6`NK9JQsEI|^b+2pZ_H-Ag%4n^zY7Uw|aXf8GTara}4WH11#XqfBa=wZCHvAJo1$Mhb{1!`T|@Cj_RAgAIn ztrM>l2kFb_s#!vZ9tfUue$K+*Wy~tgZum9rn-a?!``@aq950_rcFvQ%vwtEnG_cD5 z$UN%%(0i6*I%FZ^;InD zlkZyq%bf#fQQ_i#+(U_K`*JeesvmxLn(Giu9fY+2su@Y&rg?3kH}umso9UUK1V{id zsmGX5`iJh@PO`_&v7u88f|4$!qzr$f1gIRZ>{3e8iWQFg{k30L>K=*EI6ozgu+kDt zM7%j-3-+MKr`Y*@iAlyP1Q5{i|PDvq3VA4cjH+Uh^E0FTm%-St9y8gJ{E<)0A z9^e8-6dy~cc#JT@T&XCdsu=Jup`Mtfqi{0h&9LX&J+4U z5JSLa^}O}&tc(!+wVo`ttdW6otq|EmzV;O2PuS8`)q){a?9V_SOC#;$;ch8_VjviQX-E2OH@3)7?Q+=_D!aa#Cr!=FZqqFlY|5|HV+dj1pu;g-eg{nH5XQJG=FMs|y z-5A(8+oJ>Iv!aTstcewEtbP(>NAUA{EoG=yx2;4Npi)dMhdU2y|af zP3_BO_-b(_Am;0Rm@CT&&>biG2VN z-nTB!dwIaF&*YL`WlwMedS_>#6g8H+x_OI_}j> zIl*BU4;&U;r$C$|1<XK)ZxFaxBHAm_BN1tqpWAmPUJ3>T9AMJMJ( z+jv+7ax#g|Q7!R!`$I)t`R=Da+crUz%TK zeBwj**rhYdX6r59&hkMv%#?eC3Yc3CIMp7JUKmN}4_I)p5Sc6^lh7bXe`i9G zw_xf4fgKX!wgTh*dLPEF%b2|N{c&;pP}Yv3oB8|o1|hQ3^^0L`;mz|6;n>ZZGGo~B zJr_^ujdSn4p>^u1Hudl4ULy#II)Lz2++m!OC!YJDyX#YoPj$5D3f(mBeX|-RI;t^o z@uc^fs^xY=ihL*5%Jh=H%WJ;}3x$Bls}JR{hxW9V!`u`{nmzhu4LPWs! zu2AZ8Yv>#Jf$b?&f7hnoRs_C|Q6Lw0y`*;nkLe)w9&98k77+=rnc+$|lt zbx&p61NpXH_~T+O$o*6d*O|3-3D3yVihS$HfP?AnTvCCf`cbNrh>C5Ji+9KZ@SF4NM`XkNjNV0-M;hbd&Q)|$+#ScF#LK%U;#Opr#@mGUt zJd2+Hr$8{Lps4&&{AM`g)8N4_%cDj;JM=e+iR~Grh4dWCsx2mdn$-noZmwMKJt5-w zHoLV`k(^#T!CAg^SGmFbEvs#?rL&Zc&DSx8H{HNzG)@=q6~u`}G(G=bw6xSR_-ohF zB0ULn7rA6adr@ktR+tUt{ERMnl!{cw&TFh`9WKT1X!DBM;o#|dmZD46gwoolO^dfK z54G4yPD&V_{n@Wf5XlC&0oaj~GM|$2y2_C~eU9(C3uWv)4dEYis-0Q-xzCXw^8)yt zZ=&J@o5`3y*jl5wEi(-_ZW-!Q6^mE&lizVI`o!$H(_5@=H(pTn6<4f_TwT6DDC@pn zF4;`b zZ1^2VjsIMl3I@sJYF;+ixTYsL-l>DLf!>PEzQm_pbtCr0Z(3oB&aV6~h~sCUPB0RU z-qgvkdo8r~<3o07l$70iQ|fB09!+YOx%0KS?akP&uz0j;XR3P(ZkCYeyjjZ{WfyR# zT+l#uMEmjwRg1;i%k(=iXDMRkTvof!5y)D`(qpaj3 z?b8Dk+hn}wKSw&i0*?K;P=XVA=MZ?+mOQ)lket9(!)?3md1J5bGhaC-k}|GLE(j%R zWoScPrL-)q@JQUiZC>B`rQ#p#S1En^3{~j+QFa@PD}gYGpeIsf@FMb{0&n z+rCW(!>`7_Zk4;!HP)Yf@q~X2>b*+y)NvxH#Z7v6*ONavXYYl7{ZuT1Wa^trPHE92 z{XVfo_bkqL@0P85Iz??Gw(O7K0uPxJudW@Q#q`5DkX;ICa$!U7RB`V-#cte^!#n6^KY3wiB}`dB)hlao`Sws(`bLox z$pj;S!QH?pRoJuL=ScNhw9@|9q?^KFV|Ls4@Kf?lt=2L6P2J2C_|0_ze>0@*W;0@E zn4E|Fd&$K6E;H-o9Nd4= zcd6a6Btur$A(}pKe|t%g6oTHiigvoTIZO0X=mQbwbJrd5_c*(s&5}INE{ftBl;>9ukdb?HrNyqs zQ+m9p*AN~gfuy$nnpekV+YbZo?Ac7AOEvJ_WwrTYvTH~K%L~dvAo#@e;8AkmVA3E& znjKpXgUCuj5Q9_%&D*!eZ|$w9X=d=_gInbJ9tZqF|0wTVoX$!t<0p` zKq4*72O>U5F(if4ylN@-T(gln75ICP`ou8$xl6`FkJo!9+@Foxw|qM56jwSF-VWVS z9%KCLSV*_i-5RPj5W3ijq=VZ5$o=pwK)h{dYy2%` z8JuBwnO!4OuWYMWyRO$`@@%MEv&gRwl+Nvi)K(b zuTq5#WY{OS@ym~)dmiDo^t0x@bQMPh!Xd@*I(l4N%SHE9i2ij|RH|?E*)kJTmAnCNhI^gw{E}e0k^%6F2ZReXkGABw}wT3C@R!B|Jj8$gV`bTC^7#`*tAv zy%D4+)M%^~jdVM41OwxJ>owXnxoz3E!YHygH*W~9 zJu$DZgJ&C;j?V_JW1l>zl6Ttsz4Vc`xK2+Bl4h?}AS4kZN8Kkp6vuX({*Bb&QH|6?cacOC~uYGd9m4m3?u2FO={`$)dKZ6%L~Iyq_B0EGky$ z`nfh8jJRFd6n;mYH7tYb7{^=&!^Pnj^3K`OLidp|tkcXZ%7&}?jaT~>0)tay)yIM~ zeTJ!b?wMt4#ixwa6XY?L%oKaWW@R=f(7AT5yISXLNUeG-`q(>GgTr4psAT_mSi;p< zk7|9E*}wTFif$NX8P22HGGdA}3-u!O$~c&=-8}j3!gJp3FKywE$?i4gwQPCPsFez# zf`>FyQS~$Qwe46sZ@ut!AfHs+e=TxhQWb_@W{)MN-O+N^qMM($(fX1==$_X_n-;A7 zoAI%TlqZ_c4>Z>qeEFV|VBnk#7}KEbU9v<#;Fd33=EIs zalhuakOpWj4aU{-^b*a#$7kWY?|4+0#H*?$?NqJ*{g^H}{N84cP(F^PHSfF^aKDq6X+nCC^viO@M*ac^T+Sxht zy8T8JTkByWN~~@ncJ6)YH;H7T8}P(wR;a-z)CawGC>ma=c@le;ubcYh`0RGfVwWn1 zIN)}4ib;2Ab?|_@jXv525@CZkvKb=zj)wi6)SEl9F)guGL^g|3eKE=J-i(4Oz#RQjImqCXXqY zaVB`WIy3*g_Pu&DeJnbBk3ckYmGs2R>KI?3+Sfgr8fSTYt!e;k!2N{3y18x_m0Ca> z8tL{Ei{sh%+?wgvG19gIwIEmOF?5k^u5S>)KF@Cw(ImfkcI1?7T^WlUww zEFe|J)I~S1;ZZyqiVT)yuc1ju% zy;CnJvlpk~pB2_)ewkN3@MBW$%l!Czqw%s<)C?~h{bmfVRYo&ASs8u?3N$VYUWWh-?rMkEx+n~yk50l%y zZjzN3ndx#Z92)SC#?OWyYge;2cswONEYVY1usV`0;o6;(%u-v=b!xqDnf#vhu5_S{ zV^%lxY^XKoVqXk?A@YhJWn%H8F)FY+2dm$x1YW}Y2ln|7tL~tCm=DW)W%>&%6NXlI z#Ip+nPt1B{<*WLra8)!4MI;a*m3+jWxj*@fzl)bwP z?@{D<7xn7F+}mxBn0x&`Ur+Bgf3zk~l@>|1Uf@}cK2g&`X1I{~9KwbFz~DL%Nd`05 zF4bb_i0 z+VVu0UrAr=K!3U2G_SWF!24|u*wN(i_dr(HKSaKf+VZvD<2O-wqeYJN=n>k0Hal8K z{>NwdP@B%obC3RC?|h6-E_EzRZXhYtq_A_5{-?0YeytC8JsH}<7T%Z6vFMD=<|tlp zyJ9F)yVowtCKm(@U*VR1*Llf7U{|$;Rgt``_2oyi?p)?)`oNgDYUS9^^$Lqx?6hpX zwVrN|Bz!!(`L#L0Y9Ms&TUgr8eHOap82p7gnZtkYxCnsy&bN=7B0{7|z6S+GQHITT zlpx!+-x}#+yv#?wg*+XVz$WKhr1=x@%|kE zmf5uWn9BLTMvEtqzQjx>CEey$KZ^|{FXDcgios=?&xb7OEgzPjP3D?R9}LjVMnvyJ z;}N`nwf^DwpX5UAb)%-;f84g;Om&YQMO%p68I@K z&(-c0uhvt9D`aFUCcCz=f+S(ItRf1FNc#n|HhZaBA>X9Um)BXQ93J&EL;8#1imzba zU~-!DbKqw(hmg2Xr%hsGVQ+7@EU52TTp4p8la|1#&$z#hn$LZcs8=PDkZ<<8Gyw!I z(iMcGKfJvSl;yZAEQ%7*vI=C6P8$%amoxbKAQ4fRc!m9{>~kQTWQ|(r)8EVCM$f5nH&vQ%}P2 zvT9XNz3dBZEdOBs^$yPx0Fhqo-S(R9C%)AmMzIP4d<{5kG!Yf6WaZ28r^#>3ayIC+=}>&VBsQ z0bZT__z9!4`?_w=VcRDT%O2z5j1}_9A$#9b+nqF&q}k1p@}66bdyGNYJUo`f(Jo6f zrUDrU#=kK4`5b;AeDzhlBdNyT!&aNBFXflp-FsCCvRZ6HxRtqBzOduG%PGH#lCO~u z%@^5zl23k`>n51_AJz1s)5@NwBwNX1qoo-EyCI4Y;bP|vMF0-ZZo5oKm;^pBMGZG}xlH8Reg^TO~KE{8pd0yvx-~UX|n& zx2=Z?5a<`lYQ)zu!~^I#K5Mc^_RC{jSchTu+ch_5GEP(*A)BN=i!RHg9p)L0Yo!s7 zrDpd?(wzJa#ox$;j#Bn;Mjl(sv4bde^d?osD9--ye$qp?;>x2*OxrUa^|;hdPLrUS z{8GHLD;`xdrZ>uyaAZ)N*llk){Fp6bWGueEyvIn-CRJG+qN@_i~J zx{h?(h9{kGKsBD(={Dxxc;~rE3#{uE!;KGbJyd6chtmLdMfg^_`#kqognrkbC1xx{ zjfBr-d%`j5T}n@CscKwbmL^}`%!G|M4m+&%#Mb!cPHddndEmqp^NCLUmi$3-?7@cf zz$#VneQ}40EW`Y$7rl|^L$J#O;x8GN>nK-zs#-MszAN>XB~O~Nj(nd8k^dn3j<;a1 zMJAsiK9FRpz)PlBlxDiL9*t4@Okba@z{A+i?T^vVl7Mjb>@(nxbGeM;Y>moMOVwn zXRFuV(p?vPWNrZsKZ%?xEZ@~^#v*08>yJGS`YA}Twlg;@FtCku{r->|XA^GO7(Ngk zSm*~Ec-d3t!|V`{yMiNcIiTNL@)Es83j~@BGq^8}mt{C$fo)HS%ouQJeo5qA@T|>L z%W(|<`Asnf9c^NbOB}8oYo(88!@@kU*Gq9rOipOr8OIOJ#yh801-Blkq6FK2c%FFt ziIyt-hUUjOfuNk(FAA;?q;@yD?r6baN8RKbH&D3W=Ufbtc;5_q`MrgYikqrW>!wU zDzJ5Yw@D6Epxrol z3VY&HAxL6XtV|T&t_-&-J;u26U zR+12An#fe#wN&7A514Z-gez6)Itp>aKfl(GL3<)|znV<)xjd1?BFBO+t?_Cfj= zlhV7u_`chEWdTx zMT=d=u*n^})*d=0RB;y3#%*f0BOIRaj5L5^h~cd)@@pCaLl?~J<~ljZY`}t9i;r{^Ti?xpJ<-=lsMF;>Ff>$Tzq-1TOExOS%a=?5T6yYLO4aVO1PkRXh{rLGMa~wCp zlWq=z&A?NYFPsOiml;=y#yn_l#o7_E2IVDN8~OUa{t27%qWvdO{QOE1*NK4$G>+!h z|TZfCGlbEhO&&N`1 z__Rux*;)qSw9L3%K3@rib+ z>!!b^WMey2j3?82qUnOZHPz}5Z~4sT+Rjt-C(aib&y~@7rdwdJbDS3V9k09qe8DsV zmSZ>>0Zl6X_We60-;B;L8pOTk39t581UJ}5kb;i{bKZ`F>G&7E{-0jPGHU)t*Mj%5 zfWh%+Eg4Nc43D{eZF^Sa1K`OWw=67A|E?f`4_OyZd#IGw*Ur2%lrkFY>51#=95II~ zJTub`bNzugbSET{X`Zsb4=RJEn4J?M9+ri<^IOTBKG(_yqQCSG6kkK{#J#58sb=m{ z(=?w=l)3TK%fF@UjSpRI)RvRJS4b8opKfpF++OH-dekg6G>sPbKpA$un&zuoL_Pe< zguw1K+%ehn?&)Np%4xbM7n*3Ks^Z<;h8o zb>|Y1VD;W*zMjI_zU??{p?Cw=yN$r8>Bv`&nntyiJO%}`ZQpzGQ5-XKWRH2B(tZ7Osk5mG5TD1@5>&0j+Fchv4(u;KaA4;^haV?Z;6pNI+ig21$qVeA zp5>ji$Q%p}WL+eosom=l|MX~umnISY!2V9g#f#RL30;SUhzw48p1tAjL!Hzo`K?3J zWk&g#E=%>4xb(Y6Y{{CPt{slT3q!g<5+gN!`mx)aR)ltFBnX5kUlPX|yK^&kV{Cj6Hsl$wrFvRQwH~_qXGVM5(x`{-u0xEJyAY3kgtgr60e*Z)}t% zhacUE|6B}9$$^dAEdWkgcL;_x-Hp$BMi z-dH*F0>-tH9ZZJU9{-yAOkg$skO0m%j&J4;;~OM4HDkdif5OCT0oxlY>=!kQ8_iQy z6dAlH-v62VwS3ck-w_F;TDu%G81ddzQed2_nihmJsU?Hf6v;GJ^8jW<_gZ2qA2vW4!Mn>Fy1pljQ8<{8M>Kj>rPY& zJVz{}R32ZaNMjnALpzU#>N0HoWMDp|Ir99lCK9QK)C5208GbJI^>gqK2q!xzNn>&* z%?Y@e+${QP$;<2|@Cw5p{U#aTb~e13wRI?dHX(9pA^R%x5ypG_A6EMk*H^3$p~Fy- zKl(>)(I4Crb3)IPvfIz~%ubEH;D_Oxy(AXGQc_RrQYf+P3=b|dg}k}RA-8NN>jSHR zHe+~hx4)^VOM`XYmMN7|J?w46NqxG4=jIuGr{DPZQs3ocx`Ifv`2Pw z>A`F@8tx!9rRDR?By-B6?5fH?G?ZQAmkbyAop1hOU5mW(M|XQ1I}OM90j zf8Ht-$ecFXP{?i0ZUBw0vWmEm7SKt|uTQsZg@HzeAq<}tQ##z7%CxHOQ2B5f**W){ zFk9hFT^7`fl&f}6MZNxI-si@Hjb+T-xo>S9!`;>o9*_*ad{C*Z--zcrLYQ{B`mFzO z9n^NdX;jZWR>moKv|nO8x$c}w2*WAJexvx>-h=V7F+eC=Kc9YLZ{ePDbH8_JNI3dY zIUOOkFvEuPrjS5?B1*Y@GMcK{C%*5_VU2E>+o6#Qj4wxDHj%mx@U)Y5Sso3=x9M6< z23QC0S=Vt1zjaHdNmC%^oWvHFPF^4Py1 zn6}+DH4Lszx29~6R-&NhwJhYPQrQ z`rk;n|FiHruV%7fQ4VOpHw7(wT-pG24u2nO_IXc5K&LzZzp7*uc)0(QNIb-A69HWA zSmrr^SRW)1#0`|+FOJe9|CQl679!6NR7F7Z9oP3)`aQ3hj|0NA_Z3EufH>8->xtP= z2I-_nZ*Q;1_P2t<;$jJUNjp0h4IRfvAf`r0phibkz^nddzbPav3|%%n!PF7zd$H`m zTMvY}FX`!*L+CQHfUXd9!U5394eNq8jNfZ(_i+pfiYqH)%h0#nEF8o{M`L4m?<2xM z>#0&ndP#M4JokA=l=%2~LjgC0;)C4pk^->Jne=`TWDN`@Po@C%1>o?Jk2Ja4@7J$J zeo6fB;nzhwI%_%L)&YT}rKRP(V>c<#Wc@dU;k}XRTRjNORnKGjkstg93e<#HY~7ek zfNh9x|KkW5NSPg1yZoE^C6SOGMTcrf2ZjXMo+KtUnGv=rw!QOls{+6lv_>>v>Svu(jM> z?_7g%8IBSM>Z@U0at7FSMNp5`i1J^xKueaMm{?FV*_fRzIyF8n(OJRB z$~pzcC0N+=`0L~>NmU)xPoTJae@sziqRIVW5*?2T^|rLcxCV?tv%|8Ot!Bbvg>f*5 z8*e(E>5Ga6oO=icyoVj(;^J<3?>9(IO-=0pR^v7h4XAoIFOo&bTbIbn%AO7RopZnz z4*WDU-o3Ldq1u@C1u~KAE0GH)7Z{grTc*%OY5zZ-`z>(7_cuO7zBb?2ht`$ z;{{?xPk;mntrj0>3Xt}N$fV4JcHX;o7L~QgsHr_q)OFLW7r(dkrzf^puQ`R-{s-H9 zc6CoB6OdQF2V$VQc_(xrXA*UHd{J3#!vFg}Yx|8QJ^`)E(aJ9!w;59%ryd%A%UN~6 zMNLbS14RHdG&CWysYp_R>1s!2;8bp4(gyPR93`AC}z-r%jk_Z51EXc3IRYJ4Hg8^L`%=Z3hMQnl` zis}DTP>eH~R6Qwp($4|x;dqS|!gqKBw7`>P`cHpepY0^SG8BvIb_222Q9sAfA<%iS zLGFB5ejJJ+ic3H>f_PelfdbMp|0ii_Y2I`NOmg8TNjTo{I~di$@%Rp5wYCSNRE&yg0P4-(cATNU?I|5K!69I{tC(Ij2ia0qrl~h#3 z939!jgE99i>XDxi`~)!Uo#C}jkJ!=_=%PgKc)`zNJMRL4)K9Q_AOBqL2nO0YK>v5& zn(i^_SGWXfOHUxn{zpsXIKVX(#FYV5btg-KPuUHA`u}`4JJoW|1#}Hv;K3L#85z-U zu+01cuE$O3L(+lohypN#pl2gEzCh#F0Mya<)5C;pp)J0MQS%Ta14`J2)kuM1Eve25 zZy@WO0lEP&*)|Xgi z+J~2un~P`#JZoY9=u*8*FQR)D?e+$UKf>qinlN6`R0BjMP95k<<8!Xx%n9@2 z_=9}lc-lDX(Wh5Z?G>qlo=#b6<7r(#k2UoB|+U z`b_rc%&UX+1D24C7Q2|s&-n)D2Jk?ME3mB4lC&QHjmk-w{_O`~4;hd3~y~g`Dg(2`u z_)QCuKyA~wQ@T1T%en?MW`7X!H-m*rC~V)|2HKKdU(XAk6Tkp8`1i&}`8^I_0L8D* zVH--l4hupgm&Da#Hb4Ye`Vhz4OGh9GyK05sh#(m7wW|z+ewDBDu}H^@G*}VOR#9K8 zEXeQ*?d+8BgYD=$AODd?JVO95snPW>?;|z2?HK{-&F#K>YsbzR@GK2LKfnjSJ>m1a zHVuFe z3ctH(ScTWQ|DOQ20!aPGE{%h67{|XQmJP>R@KMWhvD%MEhjRPL@lFWe!|XA8-jkSq^*-{kk3 zoMdZji*!28{QNw*T#o(yeZLUn?d`4Bc_eU}E))5L`}=#2kB@O2hj2JdG#Vw5NN{*~ z=pSQQ76StV)Ya8tjKQ{Ty1Ke(XlS6hxtT;F!RhH~Ro8P}m-F*;hKGkS#?ap0PJe&D zU#JqGv$K=#?ruV%5Pf}pTwPrO5DJCxJdbQP>(^_uZTqi250UruCL{6*uIo}Rm;J(v z@LC=F#|C#lHlc#oU|L&S7?>l}gn`I17aWkw}Eb#>O}2zqq*Yx4(BW1Te6*8QZpT9Ea`gZL--cu~>|ek&%DiGC;mIg^WlI-Z$oIZEdB#zMj?9RljTH?`&>v z0Ev{@ZSr@^vU= zL~796+Y3M{m11sg4uGktDPCS)n4O(vY;26>>nH)WM^jw$8p%*-Tg3rW@d(bKF`F&1dEG{B$LUi{;Baik4z>*DwSeJB002ovPDHLkV1iHwN4x+4 literal 0 HcmV?d00001 diff --git a/report.md b/report.md index 1e5017e..0dc1f2a 100644 --- a/report.md +++ b/report.md @@ -1,3 +1,20 @@ -# Homework3-Policy-Gradient report +# Homework2 report +In this lab, I complete the some parts of different kinds of policy gradient. Following problems I met is what I think worth mentioned. -TA: try to elaborate the algorithms that you implemented and any details worth mentioned. +1. For Problem 1, I didn't notice the activation function tanh is only for the 1st layer. I set the activation of the 2rd layer as tanh, too. Although the network could still converge, it took much longer time to solve the CartPole problem. I tried several times and the shortest one is solving the problem in 120 iterations. Generally, it takes about 160 iterations to solve the problem, which is 2~3 times slower compared to 60 iterations in the correct implementation. The loss curve and average return during my first slower implementation is shown below. +![alt text](imgs/wrong-loss.png) +![alt text](imgs/wrong-award.png) +This makes sense because tanh function maps the output of the second layer into (0,1), and the softmax function maps the output to (0,1) again. The relatively numerical value makes the gradient relatively smaller and thux, it takes longer time to solve the given problem. +![alt text](imgs/tanh.png) + + +2. Following table shows experiment results I got at last. + +| Problem Num | Algorithm | Num of Iterations to solve the problem | +| ---------- |:-------------:| -----:| +| 1,2,3 | with baseline in gradient estimate | 70 | +| 4 | without baseline | 80 | +| 5 | Actor-Critic algorithm (with bootstrapping) | 200 | +| 6 | Generalized Advantage Estimation | 76 | + +3. Actually I found the number of iterations needed to solve the problem is unstable. Take problem 6 for example, number varies from 70 to 100 iterations. This might also depend on concrete algorithm. \ No newline at end of file From b60bd9d33fc88e0d717ad05debbd44aa9f80ee55 Mon Sep 17 00:00:00 2001 From: vufg <23201083+vufg@users.noreply.github.com> Date: Sat, 20 Jan 2018 14:46:54 +0800 Subject: [PATCH 3/3] Update report.md --- report.md | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/report.md b/report.md index 0dc1f2a..a38b09f 100644 --- a/report.md +++ b/report.md @@ -4,9 +4,10 @@ In this lab, I complete the some parts of different kinds of policy gradient. Fo 1. For Problem 1, I didn't notice the activation function tanh is only for the 1st layer. I set the activation of the 2rd layer as tanh, too. Although the network could still converge, it took much longer time to solve the CartPole problem. I tried several times and the shortest one is solving the problem in 120 iterations. Generally, it takes about 160 iterations to solve the problem, which is 2~3 times slower compared to 60 iterations in the correct implementation. The loss curve and average return during my first slower implementation is shown below. ![alt text](imgs/wrong-loss.png) ![alt text](imgs/wrong-award.png) -This makes sense because tanh function maps the output of the second layer into (0,1), and the softmax function maps the output to (0,1) again. The relatively numerical value makes the gradient relatively smaller and thux, it takes longer time to solve the given problem. ![alt text](imgs/tanh.png) +This makes sense because tanh function maps the output of the second layer into (0,1), and the softmax function maps the output to (0,1) again. The relatively numerical value makes the gradient relatively smaller and thux, it takes longer time to solve the given problem. + 2. Following table shows experiment results I got at last. @@ -17,4 +18,4 @@ This makes sense because tanh function maps the output of the second layer into | 5 | Actor-Critic algorithm (with bootstrapping) | 200 | | 6 | Generalized Advantage Estimation | 76 | -3. Actually I found the number of iterations needed to solve the problem is unstable. Take problem 6 for example, number varies from 70 to 100 iterations. This might also depend on concrete algorithm. \ No newline at end of file +3. Actually I found the number of iterations needed to solve the problem is unstable. Take problem 6 for example, number varies from 70 to 100 iterations. This might also depend on concrete algorithm.