Skip to content

saravanadivakaruni/Deep-Reinforcement-Learning

Repository files navigation

Deep-Reinforcement-Learning

The Deep Reinforcement Learning Course

by HuggingFace 🤗 will teach about Deep Reinforcement Learning from beginner to expert:

UNIT-1:

"LunarLander" agent that will learn to land correctly on the Moon using PPO architecture and MLpPolicy and the trained agent is uploaded into the Hugging Face Hub. LunarLander ---> Result

"Huggy" the Dog to fetch the stick and then play with him directly in your browser

Huggy

Result:Website

UNIT-2:

"FrozenLake-v1" where our agent will need to go from the starting state (S) to the goal state (G) by walking only on frozen tiles (F) and avoiding holes (H). FrozenLake-v1 --->Result

"Taxi-v3" will need to learn to navigate a city to transport its passengers from point A to point B. Taxi-v3---> Result

UNIT-3:

"Deep Q-Learning with Atari Games using RL Baselines3 Zoo" This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4 using the stable-baselines3 library and the RL Zoo.Deep Q-Learning with Atari Games using RL Baselines3 Zoo--->Result

UNIT-4:

"Cartpole and PixelCopter" In this notebook,coded first Deep Reinforcement Learning algorithm from scratch: Reinforce also called Monte Carlo Policy Gradient. Code your first Deep Reinforcement Learning Algorithm And test its robustness.

--->Cartpole Result

--->Pixelcopter Result

UNIT-5:

"ML Agents: Snownball Target and Pyramids Training" In this notebook, The first one will learn to shoot snowballs onto spawning targets and The second need to press a button to spawn a pyramid, then navigate to the pyramid, knock it over,and move to the gold brick at the top. Introduction to UNITY MLAgents

--->Snowball Taregt Result

--->Pyramid Training Result

UNIT-6

"Advantage Actor Critic (A2C) using Robotics Simulations with PyBullet and Panda-Gym" In this notebook, trained A2C agent using Stable-Baselines3 in robotic environments. And train two robots: A spider to learn to move and A robotic arm to move in the correct position Advantage Actor Critic (A2C) using Robotics Simulations with PyBullet and Panda-Gym

--->AntBulletEnv Result

--->PandaReachDense Result

About

Hands-on projects related to Deep Reinforcement Learning

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published