Implementation of various Deep Reinforcement Learning Algorithms on various environments with Pytorch

This repository contains well documented code for various environments

Environments covered:

Classical Algorithms
CartPole with DQN
Lunar Lander with ActorCritic
Simple Spread MultiAgent Environment with MADDPG
PyBullet's Continuous space environments like Half-Humanoid, Half-cheetah and Ant with Twin Delayed DDPG
Navigate an agent in an unknown environment with DQN
Simple Spread MultiAgent Environment with Advantage Actor Critic

Name		Name	Last commit message	Last commit date
Latest commit History 23 Commits
A2C_SimpleSpread.ipynb		A2C_SimpleSpread.ipynb
ActorCriticLunarLander.ipynb		ActorCriticLunarLander.ipynb
Bandits_and_Exploration_vs_Exploitation.ipynb		Bandits_and_Exploration_vs_Exploitation.ipynb
Dyna-Q _and_Dyna-Q+.ipynb		Dyna-Q _and_Dyna-Q+.ipynb
LICENSE		LICENSE
MazeDQNObstacles.ipynb		MazeDQNObstacles.ipynb
Optimal_Policies_with_Dynamic_Programming.ipynb		Optimal_Policies_with_Dynamic_Programming.ipynb
Policy_Evaluation_with_Temporal_Difference_Learning.ipynb		Policy_Evaluation_with_Temporal_Difference_Learning.ipynb
Pytorch_Cartpole.ipynb		Pytorch_Cartpole.ipynb
Q-Learning_and_Expected_Sarsa.ipynb		Q-Learning_and_Expected_Sarsa.ipynb
README.md		README.md
SimpleSpread_MADDPG.ipynb		SimpleSpread_MADDPG.ipynb
TD3_Ant.ipynb		TD3_Ant.ipynb
TD3_Half_Cheetah.ipynb		TD3_Half_Cheetah.ipynb
TD3_Half_Humanoid.ipynb		TD3_Half_Humanoid.ipynb