强化学习

本页按照主题记录并梳理强化学习的有关内容。

1. 基础概念
   • RL Lab 1: Environment
2. 动态规划
   • RL Lab 2: Value Iteration
   • RL Lab 3: Policy Iteration
3. 时序差分学习
   • RL Lab 4: Temporal Difference Learning
4. DQN
   • RL Lab 5: Jimbo Game
   • RL Lab 6: Deep Q Networks
   • RL Lab 7: Dueling DQN
5. 策略梯度方法
   • RL Lab 8: REINFORCE
6. 老虎机问题
   • 多臂老虎机

Reference

• K. Murphy, “Reinforcement learning: An overview,” 12 2024.

  Abstract: This manuscript gives a big-picture, up-to-date overview of the field of (deep) reinforcement learning and sequential decision making, covering value-based RL, policy-gradient methods, model-based methods, and various other topics (including a very brief discussion of RL+LLMs).

  @article{murphy2024reinforcement,
      author = {Kevin Murphy},
      eprint = {2412.05265},
      month = {12},
      title = {Reinforcement Learning: An Overview},
      url = {https://arxiv.org/pdf/2412.05265.pdf},
      year = {2024}
  }
  

评论