Reinforcement Learning with Tensorflow 2.0

Value Based Reinforcement Learning(Click to code)

• [x] Deep Q Learning

• [x] Double Deep Q Learning

• [x] Dueling Deep Q Learning

• [x] Prioritized Experience Replay

• [x] Multi Step Learning

• [x] Implicit Quantile Networks for Distributional Reinforcement Learning

• [x] DQN, IQN, Double, Dueling, PER, MultiStep

Policy Based Reinforcement Learning(Click to code)

• [x] Actor Critic

• [x] Proximal Policy Optimization

Advantage(Click to code)

• [x] 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