Reinforcement Learning Algorithm

前言

欢迎大家入坑 Reinforcement Learning，本代码实现使用pytorch

本人使用环境

python 3.8、pytorch 1.8.1、gym 0.15.7

算法目录

• Monte Carlo
  • on policy first visit Monte Carlo
  • Off Policy Monte Carlo
• Dynamic Program
  • Policy iteration
  • value iteration
• Sarsa
• Q learning
• Policy Gradient
  • REINFORCE_discrete
  • REINFORCE_continuous
  • REINFORCE with Baseline
• DQN
  • Nature_DQN
  • Navie_DQN
  • Double_DQN
  • Dueling_DQN
  • DQN with Prioritized Experience Replay
  • N_Step_DQN
  • Distributional_DQN
  • Noisy_DQN
  • Rainbow
• Actor-Critic
• DDPG/TD3
• PPO
• SAC
• Dyna-Q