PPO-CMA: Proximal Policy Optimization with Covariance Matrix Adaptation

Proximal Policy Optimization (PPO) is a highly popular model-free reinforcement learning (RL) approach. However, we observe that in a continuous action space, PPO can prematurely shrink the exploration variance, which leads to slow progress and may make the algorithm prone to getting stuck in local optima. Drawing inspiration from CMA-ES, a black-box evolutionary optimization method designed for robustness in similar situations, we propose PPO-CMA, a proximal policy optimization approach that adaptively expands the exploration variance to speed up progress. With only minor changes to PPO, our algorithm considerably improves performance in Roboschool continuous control benchmarks. Our results also show that PPO-CMA, as opposed to PPO, is significantly less sensitive to the choice of hyperparameters, allowing one to use it in complex movement optimization tasks without requiring tedious tuning.

DOI

10.1109/MLSP49062.2020.9231618

Citation

Hämäläinen, P, Babadi, A, Ma, X & Lehtinen, J 2020, PPO-CMA: Proximal Policy Optimization with Covariance Matrix Adaptation . in Proceedings of the 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing, MLSP 2020 ., 9231618, IEEE, IEEE International Workshop on Machine Learning for Signal Processing, Espoo, Finland, 21/09/2020 . https://doi.org/10.1109/MLSP49062.2020.9231618

Permanent link to this item

https://urn.fi/URN:NBN:fi:aalto-2020123160461

Collections

[article-cris] Perustieteiden korkeakoulu / SCI

Show all metadata

PPO-CMA: Proximal Policy Optimization with Covariance Matrix Adaptation

Access rights

URL

Journal Title

Journal ISSN

Volume Title

Authors

Date

Department

Major/Subject

Mcode

Degree programme

Language

Pages

Series

Abstract

Description

Keywords

Other note

DOI

Citation

Permanent link to this item

Collections