强化学习

Posted 2021-01-01 think90

 

• 简介

  1. 1.1 什么是 强化学习 (Reinforcement Learning)
  2. 1.2 强化学习方法汇总 (Reinforcement Learning)
  3. 1.3 为什么用强化学习 Why?
  4. 1.4 课程要求

• Q-learning

  1. 2.1 小例子
  2. 2.2 什么是 Q Leaning
  3. 2.3 Q-learning 算法更新
  4. 2.4 Q-learning 思维决策

• Sarsa

  1. 3.1 什么是 Sarsa
  2. 3.2 Sarsa 算法更新
  3. 3.3 Sarsa 思维决策
  4. 3.4 什么是 Sarsa(lambda)
  5. 3.5 Sarsa-lambda

• Deep Q Network

  1. 4.1 什么是 DQN
  2. 4.2 DQN 算法更新 (Tensorflow)
  3. 4.3 DQN 神经网络 (Tensorflow)
  4. 4.4 DQN 思维决策 (Tensorflow)
  5. 4.5 OpenAI gym 环境库
  6. 4.6 Double DQN (Tensorflow)
  7. 4.7 Prioritized Experience Replay (DQN) (Tensorflow)
  8. 4.8 Dueling DQN (Tensorflow)

• Policy Gradient

  1. 5.1 什么是 Policy Gradients
  2. 5.2 Policy Gradients 算法更新 (Tensorflow)
  3. 5.3 Policy Gradients 思维决策 (Tensorflow)

• Actor Critic

  1. 6.1 什么是 Actor Critic
  2. 6.2 Actor Critic (Tensorflow)
  3. 6.3 什么是 Deep Deterministic Policy Gradient (DDPG)
  4. 6.4 Deep Deterministic Policy Gradient (DDPG) (Tensorflow)
  5. 6.5 什么是 Asynchronous Advantage Actor-Critic (A3C)
  6. 6.6 Asynchronous Advantage Actor-Critic (A3C) (Tensorflow)
  7. 6.7 Distributed Proximal Policy Optimization (DPPO) (Tensorflow)

• Model Based RL