策略引擎>> pytorch-ddpg>> 返回
项目作者： zhihanyang2022

项目描述 ：
Deep deterministic policy gradient (DDPG) in PyTorch 🚀
高级语言： Python
项目地址: git://github.com/zhihanyang2022/pytorch-ddpg.git
创建时间： 2021-04-14T13:36:24Z
项目社区：https://github.com/zhihanyang2022/pytorch-ddpg
开源协议：MIT License
下载


Deep deterministic policy gradient

A minimalistic and friendly implementation of DDPG using PyTorch.

https://spinningup.openai.com/en/latest/algorithms/ddpg.html

TODO:

  • simplify buffer
  • requirements
  • think out how to easier switch between different variants
  • important features and variants
  • hyperparameters
  • training curves and standard errors
  • action wrapper
  • some design choices and justifications

Credit:

Leadboard performances
https://github.com/openai/gym/wiki/Leaderboard#pendulum-v0