Skip to content
/ CPO Public

Constrained Policy Optimization implementation on Safety Gym

Notifications You must be signed in to change notification settings

dobro12/CPO

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CPO

A simple Tensorflow1 & PyTorch implementation of constrained policy optimization (CPO) on Safety Gym.

requirement

  • gym
  • mujoco
  • safety_gym
  • tensorflow 1.13.1
  • pytorch 1.10.1

how to use

tf1

  • python train.py #training
  • python train.py test #test

torch

  • python main.py #training
  • python main.py --test --resume {#_of_checkpoint} #test

reference

About

Constrained Policy Optimization implementation on Safety Gym

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages