强化学习文章阅读顺序

1. 马尔可夫决策过程(MDP)定义整理
2. 基于模型的动态规划 Planning by Dynamic Programming
3. 无模型预测 Model-Free Predication
4. 无模型控制 Model-Free Control
5. 值函数近似 Value Function Approximation
   1. Deep Q-Network
   2. DQN 代码实现
   3. Double DQN & 代码实现
   4. Prioritized Experience Replay
   5. Prioritized Experience Replay 代码实现
   6. Dueling Network Architectures for Deep Reinforcement Learning & 代码实现
6. 策略梯度 Policy Gradient
   1. Actor-Critic Softmax & Gaussian Policy 代码实现
   2. Deterministic Policy Gradient
   3. Deep Deterministic Policy Gradient
   4. DDPG 代码实现
   5. Deep Reinforcement Learning In Parameterized Action Space
   6. Asynchronous Methods for Deep Reinforcement Learning
   7. A3C 代码实现
   8. Trust Region Policy Optimization
   9. High-Dimensional Continuous Control Using Generalized Advantage Estimation
   10. Proximal Policy Optimization Algorithms
   11. Proximal Policy Optimization 代码实现
7. 整合学习与规划 Integrating Learning and Planning