Reinforcement learning 强化学习

[[ Reinforcement Learning 强化学习.canvas ]]

Terminology 术语

RL 概念

RL 实现过程

RL Observation and State 观察和状态

RL Action Space 行动空间

RL Reward and Discount 奖励和折扣

RL 任务种类

RL Exploration and Exploitation 探索和利用

RL Policy 行动策略

RL Value Function 价值函数

RL 学习策略

RL Deep RL 深度强化学习

RL Off-policy and On-policy 异策和同策

Markov Property 马尔可夫性质

Markov Decision Process 马尔可夫决策过程

Bellman Equation 贝尔曼方程

Epsilon-Greedy Policy

Algorithm 算法

Q-Learning

Deep Q-Learning (DQN)

Courses

1. The Hugging Face Deep Reinforcement Learning Class

Resources

1. http://incompleteideas.net/book/RLbook2020.pdf
2. http://huangc.top/2018/05/03/RL-2018/
3. http://huangc.top/2018/05/12/RL2-2018/

#待整理笔记