k8s/Kubernetes>> PPO-PyTorch>> 返回
项目作者： Abhipanda4

项目描述 ：
Implementation of Proximal Policy Optimization(PPO)
高级语言： Python
项目地址: git://github.com/Abhipanda4/PPO-PyTorch.git
创建时间： 2018-07-18T05:09:41Z
项目社区：https://github.com/Abhipanda4/PPO-PyTorch
开源协议：
下载


This is a Pytorch implementation of Proximal Policy Optimization as described in this paper.

The implementation used in this repo was used as a reference for this implementation.

To run a demo, clone the repo and use the command:
python simulate.py

The training plots are shown below:

reward plot

actor loss plot

critic loss plot