xiaxx244/tf2.0_reinforcement_learning

Basic reinforcement learning implementation with tensorflow version 2.0

Reinforcement Learning with Tensorflow 2.0

Value Based Reinforcement Learning(Click to code)

• Deep Q Learning

• Double Deep Q Learning

• Dueling Deep Q Learning

• Prioritized Experience Replay

• Multi Step Learning

• Implicit Quantile Networks for Distributional Reinforcement Learning

• DQN, IQN, Double, Dueling, PER, MultiStep

Policy Based Reinforcement Learning(Click to code)

• Actor Critic

• Proximal Policy Optimization

Advantage(Click to code)

• High-Dimensional Continuous Control Using Generalized Advantage Estimation

Reference

1. Deep Q Learning
2. Double Deep Q Learning
3. Dueling Deep Q Learning
4. Prioritized Experience Replay
5. Actor Critic
6. Proximal Policy Optimization
7. High-Dimensional Continuous Control Using Generalized Advantage Estimation
8. tf2.0-Guide
9. Implicit Quantile Networks for Distributional Reinforcement Learning
10. Multi Step Learning