Skip to content

Ontroad/EPOPMN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

EPOPMN

Code release for the paper: "Exterior Penalty Policy Optimization with Penalty Metric Network under Constraints", IJCAI 2024.

This repository is based on the omnisafe.

Installation Guide

Create conda env: conda create -n epopmn python=3.8

Activate conda env: conda activate epopmn

Install: conda env create -f epopmn.yaml

Run Experiments

Register the EPO algorithm into the omnisafe library.

Activate conda env: source activate epopmn

Run the code by:

cd experiments
python train_exp.py --algo EPO_PMN --env-id SafetyPointGoal1-v0 --parallel 1 --total-steps 10000000 --device cpu --vector-env-nums 1 --torch-threads 1

License

EPOPMN is released under Apache License 2.0.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages