search

liuzuxin / cvpo-safe-rl

Code for "Constrained Variational Policy Optimization for Safe Reinforcement Learning" (ICML 2022)
GNU General Public License v3.0
63 stars 7 forks source link

Code for those on-policy algorithms #2

Closed grandpahao closed 1 year ago

grandpahao commented 1 year ago

Hi~ I do not find codes of on-policy algorithms in this repo. Do you have any examples of PPO with lagrangian multipliers?

liuzuxin commented 1 year ago

Hi @grandpahao,

I use the original safety-starter-agents as the on-policy baselines in the paper, see the third paragraph here: https://github.com/liuzuxin/cvpo-safe-rl#notes-and-acknowledgments. Recently I found another repo contains the implementations of PPO-L, TRPO-L, and CPO, see https://github.com/PKU-MARL/Safe-Policy-Optimization. Thanks.

grandpahao commented 1 year ago

A lot of thanks for your answer~