Optimistic Multi-Agent Policy Gradient

No Thumbnail Available

Access rights

openAccess
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2024

Major/Subject

Mcode

Degree programme

Language

en

Pages

17

Series

Proceedings of Machine Learning Research, Volume 235, pp. 61186-61202

Abstract

Relative overgeneralization (RO) occurs in cooperative multi-agent learning tasks when agents converge towards a suboptimal joint policy due to overfitting to suboptimal behaviors of other agents.No methods have been proposed for addressing RO in multi-agent policy gradient (MAPG) methods although these methods produce state-of-the-art results.To address this gap, we propose a general, yet simple, framework to enable optimistic updates in MAPG methods that alleviate the RO problem.Our approach involves clipping the advantage to eliminate negative values, thereby facilitating optimistic updates in MAPG.The optimism prevents individual agents from quickly converging to a local optimum.Additionally, we provide a formal analysis to show that the proposed method retains optimality at a fixed point.In extensive evaluations on a diverse set of tasks including the Multi-agent MuJoCo and Overcooked benchmarks, our method outperforms strong baselines on 13 out of 19 tested tasks and matches the performance on the rest.

Description

Publisher Copyright: Copyright 2024 by the author(s)

Keywords

Other note

Citation

Zhao, W, Zhao, Y, Li, Z, Kannala, J & Pajarinen, J 2024, ' Optimistic Multi-Agent Policy Gradient ', Proceedings of Machine Learning Research, vol. 235, pp. 61186-61202 . < https://proceedings.mlr.press/v235/zhao24v.html >