简介

1. 1.1 Why?
2. 1.2 课程要求

Q-learning

1. 2.1 小例子
2. 2.2 Q-learning 算法更新
3. 2.3 Q-learning 思维决策

Sarsa

1. 3.1 Sarsa 算法更新
2. 3.2 Sarsa 思维决策
3. 3.3 Sarsa-lambda

Deep Q Network

1. 4.1 DQN 算法更新 (Tensorflow)
2. 4.2 DQN 神经网络 (Tensorflow)
3. 4.3 DQN 思维决策 (Tensorflow)
4. 4.4 OpenAI gym 环境库 (Tensorflow)
5. 4.5 Double DQN (Tensorflow)
6. 4.6 Prioritized Experience Replay (DQN) (Tensorflow)
7. 4.7 Dueling DQN (Tensorflow)

Policy Gradient

1. 5.1 Policy Gradients 算法更新 (Tensorflow)
2. 5.2 Policy Gradients 思维决策 (Tensorflow)

Actor Critic

1. 6.1 Actor Critic (Tensorflow)
2. 6.2 Deep Deterministic Policy Gradient (DDPG) (Tensorflow)
3. 6.3 Asynchronous Advantage Actor-Critic (A3C) (Tensorflow)
4. 6.4 Distributed Proximal Policy Optimization (DPPO) (Tensorflow)

Model Based RL