Skip to content

Re-produce DQN, REINFORCE, REINFORCE with baseline, one-step AC, QAC, QAC with shared network, PPO2, DDPG, TD3, SAC, SAC discrete,A2C,A3C

Notifications You must be signed in to change notification settings

ThousandOfWind/DRL-baseline

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

32 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DRL baseline

目前主要是一些单智能体深度强化学习方法的复现

学生习作,以大神sutton的书和周博磊的课程为线索复现

目前已完成的部分包括:

  • DQN
  • REINFORCE
  • REINFORCE with baseline
  • one-step AC
  • QAC
  • QAC with shared network
  • PPO2
  • DDPG
  • TD3
  • SAC
  • SAC (离散动作)
  • A2C
  • A3C

可以配合以下内容服用

CSDN 地址 涉及算法
强化学习策略梯度梳理1 - REINFORCE(附代码) REINFORCE、REINFORCE with baseline
强化学习策略梯度梳理2 - AC(附代码) one-step AC、 QAC、 QAC with shared network
强化学习策略梯度梳理3-SOTA 上 PPO2
SOTA 中 DDPG,TD3,SAC, SAC 离散动作
SOTA 下 A2C, A3C

计划要复现的其他方法包括

  • Rainbow
  • HER
  • VIN

About

Re-produce DQN, REINFORCE, REINFORCE with baseline, one-step AC, QAC, QAC with shared network, PPO2, DDPG, TD3, SAC, SAC discrete,A2C,A3C

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages