├── .gitignore ├── A3C-A2C ├── A3C-my-understanding.pdf ├── A3C-paper.pdf ├── README.md ├── a2c-shang.py ├── a2c.py ├── multiprocessing_env.py └── testa2c.ipynb ├── AWS DeepRacer Competition ├── README.md ├── reward.py ├── reward2.rtf └── reward3.py ├── DDPG ├── DDPG-paper.pdf ├── README.md └── ddpg.py ├── DQN ├── DQN OTHER IMPL │ ├── README.md │ ├── atari_wrappers.py │ ├── dqn.py │ ├── memory.py │ └── notes.md ├── DQNNaturePaper.pdf ├── Playing Atari with Deep Reinforcement Learning.pdf ├── README.md ├── dqn.py ├── shape-and-arrangement-ofcolumns-in-cats-striate-cortext.pdf └── test_dqn.ipynb ├── General ├── A (Long) Peek into Reinforcement Learning.pdf ├── README.md └── rl_intro-OpenAI-Hackathon.pdf ├── LICENSE ├── PPO ├── PPO.pdf ├── README.md ├── multiprocessing_env.py ├── ppo-m-update.py ├── ppo-m.py └── ppo.py ├── Practice └── p1 - Banana Env - pixels │ └── README.md ├── README.md ├── REINFORCE ├── CartPole-v0.py ├── From Deep Reinforcement Learning to Stochastic Computation Graphs-Ch2.pdf ├── README.md ├── reinforce.pth ├── reinforce.py └── test_reinforce.ipynb ├── Temporal Difference ├── .DS_Store ├── README.md ├── assets │ ├── expected-sarsa.png │ ├── sarsa.png │ └── sarsamax.png ├── expected-sarsa.py ├── sarsa.py └── sarsamax.py └── assets ├── algorithm.png ├── expected-sarsa.png ├── sarsa.png └── sarsamax.png /.gitignore: -------------------------------------------------------------------------------- 1 | .DS_Store 2 | -------------------------------------------------------------------------------- /A3C-A2C/A3C-my-understanding.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/A3C-A2C/A3C-my-understanding.pdf -------------------------------------------------------------------------------- /A3C-A2C/A3C-paper.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/A3C-A2C/A3C-paper.pdf -------------------------------------------------------------------------------- /A3C-A2C/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/A3C-A2C/README.md -------------------------------------------------------------------------------- /A3C-A2C/a2c-shang.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/A3C-A2C/a2c-shang.py -------------------------------------------------------------------------------- /A3C-A2C/a2c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/A3C-A2C/a2c.py -------------------------------------------------------------------------------- /A3C-A2C/multiprocessing_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/A3C-A2C/multiprocessing_env.py -------------------------------------------------------------------------------- /A3C-A2C/testa2c.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/A3C-A2C/testa2c.ipynb -------------------------------------------------------------------------------- /AWS DeepRacer Competition/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/AWS DeepRacer Competition/README.md -------------------------------------------------------------------------------- /AWS DeepRacer Competition/reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/AWS DeepRacer Competition/reward.py -------------------------------------------------------------------------------- /AWS DeepRacer Competition/reward2.rtf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/AWS DeepRacer Competition/reward2.rtf -------------------------------------------------------------------------------- /AWS DeepRacer Competition/reward3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/AWS DeepRacer Competition/reward3.py -------------------------------------------------------------------------------- /DDPG/DDPG-paper.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/DDPG/DDPG-paper.pdf -------------------------------------------------------------------------------- /DDPG/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/DDPG/README.md -------------------------------------------------------------------------------- /DDPG/ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/DDPG/ddpg.py -------------------------------------------------------------------------------- /DQN/DQN OTHER IMPL/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/DQN/DQN OTHER IMPL/README.md -------------------------------------------------------------------------------- /DQN/DQN OTHER IMPL/atari_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/DQN/DQN OTHER IMPL/atari_wrappers.py -------------------------------------------------------------------------------- /DQN/DQN OTHER IMPL/dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/DQN/DQN OTHER IMPL/dqn.py -------------------------------------------------------------------------------- /DQN/DQN OTHER IMPL/memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/DQN/DQN OTHER IMPL/memory.py -------------------------------------------------------------------------------- /DQN/DQN OTHER IMPL/notes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/DQN/DQN OTHER IMPL/notes.md -------------------------------------------------------------------------------- /DQN/DQNNaturePaper.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/DQN/DQNNaturePaper.pdf -------------------------------------------------------------------------------- /DQN/Playing Atari with Deep Reinforcement Learning.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/DQN/Playing Atari with Deep Reinforcement Learning.pdf -------------------------------------------------------------------------------- /DQN/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/DQN/README.md -------------------------------------------------------------------------------- /DQN/dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/DQN/dqn.py -------------------------------------------------------------------------------- /DQN/shape-and-arrangement-ofcolumns-in-cats-striate-cortext.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/DQN/shape-and-arrangement-ofcolumns-in-cats-striate-cortext.pdf -------------------------------------------------------------------------------- /DQN/test_dqn.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/DQN/test_dqn.ipynb -------------------------------------------------------------------------------- /General/A (Long) Peek into Reinforcement Learning.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/General/A (Long) Peek into Reinforcement Learning.pdf -------------------------------------------------------------------------------- /General/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/General/README.md -------------------------------------------------------------------------------- /General/rl_intro-OpenAI-Hackathon.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/General/rl_intro-OpenAI-Hackathon.pdf -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/LICENSE -------------------------------------------------------------------------------- /PPO/PPO.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/PPO/PPO.pdf -------------------------------------------------------------------------------- /PPO/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/PPO/README.md -------------------------------------------------------------------------------- /PPO/multiprocessing_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/PPO/multiprocessing_env.py -------------------------------------------------------------------------------- /PPO/ppo-m-update.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/PPO/ppo-m-update.py -------------------------------------------------------------------------------- /PPO/ppo-m.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/PPO/ppo-m.py -------------------------------------------------------------------------------- /PPO/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/PPO/ppo.py -------------------------------------------------------------------------------- /Practice/p1 - Banana Env - pixels/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/Practice/p1 - Banana Env - pixels/README.md -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/README.md -------------------------------------------------------------------------------- /REINFORCE/CartPole-v0.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/REINFORCE/CartPole-v0.py -------------------------------------------------------------------------------- /REINFORCE/From Deep Reinforcement Learning to Stochastic Computation Graphs-Ch2.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/REINFORCE/From Deep Reinforcement Learning to Stochastic Computation Graphs-Ch2.pdf -------------------------------------------------------------------------------- /REINFORCE/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/REINFORCE/README.md -------------------------------------------------------------------------------- /REINFORCE/reinforce.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/REINFORCE/reinforce.pth -------------------------------------------------------------------------------- /REINFORCE/reinforce.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/REINFORCE/reinforce.py -------------------------------------------------------------------------------- /REINFORCE/test_reinforce.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/REINFORCE/test_reinforce.ipynb -------------------------------------------------------------------------------- /Temporal Difference/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/Temporal Difference/.DS_Store -------------------------------------------------------------------------------- /Temporal Difference/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/Temporal Difference/README.md -------------------------------------------------------------------------------- /Temporal Difference/assets/expected-sarsa.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/Temporal Difference/assets/expected-sarsa.png -------------------------------------------------------------------------------- /Temporal Difference/assets/sarsa.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/Temporal Difference/assets/sarsa.png -------------------------------------------------------------------------------- /Temporal Difference/assets/sarsamax.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/Temporal Difference/assets/sarsamax.png -------------------------------------------------------------------------------- /Temporal Difference/expected-sarsa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/Temporal Difference/expected-sarsa.py -------------------------------------------------------------------------------- /Temporal Difference/sarsa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/Temporal Difference/sarsa.py -------------------------------------------------------------------------------- /Temporal Difference/sarsamax.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/Temporal Difference/sarsamax.py -------------------------------------------------------------------------------- /assets/algorithm.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/assets/algorithm.png -------------------------------------------------------------------------------- /assets/expected-sarsa.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/assets/expected-sarsa.png -------------------------------------------------------------------------------- /assets/sarsa.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/assets/sarsa.png -------------------------------------------------------------------------------- /assets/sarsamax.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/spirosrap/Deep-Reinforcement-Learning/HEAD/assets/sarsamax.png --------------------------------------------------------------------------------