rubythonode / reinforcement-learning Goto Github PK

Minimal and clean examples of reinforcement learning algorithms presented by RLCode team. [한국어]

Maintainers - Woongwon, Youngmoo, Hyeokreal, Uiryeong, Keon

From the most basic algorithms to the more recent ones categorized as 'deep reinforcement learning', the examples are easy to read with comments. Please feel free to create a Pull Request, or open an issue!

Dependencies

1. Python 3.5
2. Tensorflow 1.0.0
3. Keras
4. numpy
5. pandas
6. matplot
7. pillow
8. Skimage
9. h5py

Install Requirements

pip install -r requirements.txt

Table of Contents

Code 1 - Mastering the basics of reinforcement learning in the simplified world called "Grid World"

• Policy Iteration
• Value Iteration
• Monte Carlo
• SARSA
• Q-Learning
• Deep Q Network
• Policy Gradient

Code 2 - Applying deep reinforcement learning on basic Cartpole game.

• Deep Q Network
• Double Deep Q Network
• Dueling Deep Q Network
• Policy Gradient
• Actor Critic
• Asynchronous Advantage Actor Critic (A3C) - WIP

Code 3 - Mastering Atari games with Deep Reinforcement Learning

• Breakout - DQN, PG, A3C
• Pong - DQN, PG, A3C