From 88fa096d48fd4e410310589c2a17baf7c9f68388 Mon Sep 17 00:00:00 2001 From: Wonhyeong Seo Date: Fri, 14 Jul 2023 13:49:55 +0900 Subject: [PATCH] feat: initiate Korean i18n effort --- .github/workflows/build_documentation.yml | 2 +- .github/workflows/build_pr_documentation.yml | 2 +- units/ko/_toctree.yml | 232 +++++++++++++++++++ 3 files changed, 234 insertions(+), 2 deletions(-) create mode 100644 units/ko/_toctree.yml diff --git a/.github/workflows/build_documentation.yml b/.github/workflows/build_documentation.yml index f626b63d..cb31c170 100644 --- a/.github/workflows/build_documentation.yml +++ b/.github/workflows/build_documentation.yml @@ -14,7 +14,7 @@ jobs: package_name: deep-rl-course path_to_docs: deep-rl-class/units/ additional_args: --not_python_module - languages: en + languages: en ko secrets: token: ${{ secrets.HUGGINGFACE_PUSH }} hf_token: ${{ secrets.HF_DOC_BUILD_PUSH }} diff --git a/.github/workflows/build_pr_documentation.yml b/.github/workflows/build_pr_documentation.yml index 3c87366c..749fe9fa 100644 --- a/.github/workflows/build_pr_documentation.yml +++ b/.github/workflows/build_pr_documentation.yml @@ -17,4 +17,4 @@ jobs: package_name: deep-rl-course path_to_docs: deep-rl-class/units/ additional_args: --not_python_module - languages: en + languages: en ko diff --git a/units/ko/_toctree.yml b/units/ko/_toctree.yml new file mode 100644 index 00000000..9bddb100 --- /dev/null +++ b/units/ko/_toctree.yml @@ -0,0 +1,232 @@ +- title: (작업중) Unit 0. Welcome to the course + sections: + - local: ../en/unit0/introduction + title: (작업중) Welcome to the course 🤗 + - local: ../en/unit0/setup + title: (작업중) Setup + - local: ../en/unit0/discord101 + title: (작업중) Discord 101 +- title: (작업중) Unit 1. Introduction to Deep Reinforcement Learning + sections: + - local: ../en/unit1/introduction + title: (작업중) Introduction + - local: ../en/unit1/what-is-rl + title: (작업중) What is Reinforcement Learning? + - local: ../en/unit1/rl-framework + title: (작업중) The Reinforcement Learning Framework + - local: ../en/unit1/tasks + title: (작업중) The type of tasks + - local: ../en/unit1/exp-exp-tradeoff + title: (작업중) The Exploration/ Exploitation tradeoff + - local: ../en/unit1/two-methods + title: (작업중) The two main approaches for solving RL problems + - local: ../en/unit1/deep-rl + title: (작업중) The “Deep” in Deep Reinforcement Learning + - local: ../en/unit1/summary + title: (작업중) Summary + - local: ../en/unit1/glossary + title: (작업중) Glossary + - local: ../en/unit1/hands-on + title: (작업중) Hands-on + - local: ../en/unit1/quiz + title: (작업중) Quiz + - local: ../en/unit1/conclusion + title: (작업중) Conclusion + - local: ../en/unit1/additional-readings + title: (작업중) Additional Readings +- title: (작업중) Bonus Unit 1. Introduction to Deep Reinforcement Learning with Huggy + sections: + - local: ../en/unitbonus1/introduction + title: (작업중) Introduction + - local: ../en/unitbonus1/how-huggy-works + title: (작업중) How Huggy works? + - local: ../en/unitbonus1/train + title: (작업중) Train Huggy + - local: ../en/unitbonus1/play + title: (작업중) Play with Huggy + - local: ../en/unitbonus1/conclusion + title: (작업중) Conclusion +- title: (작업중) Live 1. How the course work, Q&A, and playing with Huggy + sections: + - local: ../en/live1/live1 + title: (작업중) Live 1. How the course work, Q&A, and playing with Huggy 🐶 +- title: (작업중) Unit 2. Introduction to Q-Learning + sections: + - local: ../en/unit2/introduction + title: (작업중) Introduction + - local: ../en/unit2/what-is-rl + title: (작업중) What is RL? A short recap + - local: ../en/unit2/two-types-value-based-methods + title: (작업중) The two types of value-based methods + - local: ../en/unit2/bellman-equation + title: (작업중) The Bellman Equation, simplify our value estimation + - local: ../en/unit2/mc-vs-td + title: (작업중) Monte Carlo vs Temporal Difference Learning + - local: ../en/unit2/mid-way-recap + title: (작업중) Mid-way Recap + - local: ../en/unit2/mid-way-quiz + title: (작업중) Mid-way Quiz + - local: ../en/unit2/q-learning + title: (작업중) Introducing Q-Learning + - local: ../en/unit2/q-learning-example + title: (작업중) A Q-Learning example + - local: ../en/unit2/q-learning-recap + title: (작업중) Q-Learning Recap + - local: ../en/unit2/glossary + title: (작업중) Glossary + - local: ../en/unit2/hands-on + title: (작업중) Hands-on + - local: ../en/unit2/quiz2 + title: (작업중) Q-Learning Quiz + - local: ../en/unit2/conclusion + title: (작업중) Conclusion + - local: ../en/unit2/additional-readings + title: (작업중) Additional Readings +- title: (작업중) Unit 3. Deep Q-Learning with Atari Games + sections: + - local: ../en/unit3/introduction + title: (작업중) Introduction + - local: ../en/unit3/from-q-to-dqn + title: (작업중) From Q-Learning to Deep Q-Learning + - local: ../en/unit3/deep-q-network + title: (작업중) The Deep Q-Network (DQN) + - local: ../en/unit3/deep-q-algorithm + title: (작업중) The Deep Q Algorithm + - local: ../en/unit3/glossary + title: (작업중) Glossary + - local: ../en/unit3/hands-on + title: (작업중) Hands-on + - local: ../en/unit3/quiz + title: (작업중) Quiz + - local: ../en/unit3/conclusion + title: (작업중) Conclusion + - local: ../en/unit3/additional-readings + title: (작업중) Additional Readings +- title: (작업중) Bonus Unit 2. Automatic Hyperparameter Tuning with Optuna + sections: + - local: ../en/unitbonus2/introduction + title: (작업중) Introduction + - local: ../en/unitbonus2/optuna + title: (작업중) Optuna + - local: ../en/unitbonus2/hands-on + title: (작업중) Hands-on +- title: (작업중) Unit 4. Policy Gradient with PyTorch + sections: + - local: ../en/unit4/introduction + title: (작업중) Introduction + - local: ../en/unit4/what-are-policy-based-methods + title: (작업중) What are the policy-based methods? + - local: ../en/unit4/advantages-disadvantages + title: (작업중) The advantages and disadvantages of policy-gradient methods + - local: ../en/unit4/policy-gradient + title: (작업중) Diving deeper into policy-gradient + - local: ../en/unit4/pg-theorem + title: (작업중) (Optional) the Policy Gradient Theorem + - local: ../en/unit4/hands-on + title: (작업중) Hands-on + - local: ../en/unit4/quiz + title: (작업중) Quiz + - local: ../en/unit4/conclusion + title: (작업중) Conclusion + - local: ../en/unit4/additional-readings + title: (작업중) Additional Readings +- title: (작업중) Unit 5. Introduction to Unity ML-Agents + sections: + - local: ../en/unit5/introduction + title: (작업중) Introduction + - local: ../en/unit5/how-mlagents-works + title: (작업중) How ML-Agents works? + - local: ../en/unit5/snowball-target + title: (작업중) The SnowballTarget environment + - local: ../en/unit5/pyramids + title: (작업중) The Pyramids environment + - local: ../en/unit5/curiosity + title: (작업중) (Optional) What is curiosity in Deep Reinforcement Learning? + - local: ../en/unit5/hands-on + title: (작업중) Hands-on + - local: ../en/unit5/bonus + title: (작업중) Bonus. Learn to create your own environments with Unity and MLAgents + - local: ../en/unit5/conclusion + title: (작업중) Conclusion +- title: (작업중) Unit 6. Actor Critic methods with Robotics environments + sections: + - local: ../en/unit6/introduction + title: (작업중) Introduction + - local: ../en/unit6/variance-problem + title: (작업중) The Problem of Variance in Reinforce + - local: ../en/unit6/advantage-actor-critic + title: (작업중) Advantage Actor Critic (A2C) + - local: ../en/unit6/hands-on + title: (작업중) Advantage Actor Critic (A2C) using Robotics Simulations with PyBullet and Panda-Gym 🤖 + - local: ../en/unit6/conclusion + title: (작업중) Conclusion + - local: ../en/unit6/additional-readings + title: (작업중) Additional Readings +- title: (작업중) Unit 7. Introduction to Multi-Agents and AI vs AI + sections: + - local: ../en/unit7/introduction + title: (작업중) Introduction + - local: ../en/unit7/introduction-to-marl + title: (작업중) An introduction to Multi-Agents Reinforcement Learning (MARL) + - local: ../en/unit7/multi-agent-setting + title: (작업중) Designing Multi-Agents systems + - local: ../en/unit7/self-play + title: (작업중) Self-Play + - local: ../en/unit7/hands-on + title: (작업중) Let's train our soccer team to beat your classmates' teams (AI vs. AI) + - local: ../en/unit7/conclusion + title: (작업중) Conclusion + - local: ../en/unit7/additional-readings + title: (작업중) Additional Readings +- title: (작업중) Unit 8. Part 1 Proximal Policy Optimization (PPO) + sections: + - local: ../en/unit8/introduction + title: (작업중) Introduction + - local: ../en/unit8/intuition-behind-ppo + title: (작업중) The intuition behind PPO + - local: ../en/unit8/clipped-surrogate-objective + title: (작업중) Introducing the Clipped Surrogate Objective Function + - local: ../en/unit8/visualize + title: (작업중) Visualize the Clipped Surrogate Objective Function + - local: ../en/unit8/hands-on-cleanrl + title: (작업중) PPO with CleanRL + - local: ../en/unit8/conclusion + title: (작업중) Conclusion + - local: ../en/unit8/additional-readings + title: (작업중) Additional Readings +- title: (작업중) Unit 8. Part 2 Proximal Policy Optimization (PPO) with Doom + sections: + - local: ../en/unit8/introduction-sf + title: (작업중) Introduction + - local: ../en/unit8/hands-on-sf + title: (작업중) PPO with Sample Factory and Doom + - local: ../en/unit8/conclusion-sf + title: (작업중) Conclusion +- title: (작업중) Bonus Unit 3. Advanced Topics in Reinforcement Learning + sections: + - local: ../en/unitbonus3/introduction + title: (작업중) Introduction + - local: ../en/unitbonus3/model-based + title: (작업중) Model-Based Reinforcement Learning + - local: ../en/unitbonus3/offline-online + title: (작업중) Offline vs. Online Reinforcement Learning + - local: ../en/unitbonus3/rlhf + title: (작업중) Reinforcement Learning from Human Feedback + - local: ../en/unitbonus3/decision-transformers + title: (작업중) Decision Transformers and Offline RL + - local: ../en/unitbonus3/language-models + title: (작업중) Language models in RL + - local: ../en/unitbonus3/curriculum-learning + title: (작업중) (Automatic) Curriculum Learning for RL + - local: ../en/unitbonus3/envs-to-try + title: (작업중) Interesting environments to try + - local: ../en/unitbonus3/godotrl + title: (작업중) An Introduction to Godot RL + - local: ../en/unitbonus3/rl-documentation + title: (작업중) Brief introduction to RL documentation +- title: (작업중) Certification and congratulations + sections: + - local: ../en/communication/conclusion + title: (작업중) Congratulations + - local: ../en/communication/certification + title: (작업중) Get your certificate of completion