{"title":"MESA: Cooperative Meta-Exploration in Multi-Agent Learning through Exploiting State-Action Space Structure","authors":"Zhicheng Zhang, Yancheng Liang, Yi Wu, Fei Fang","doi":"10.5555/3635637.3663073","DOIUrl":null,"url":null,"abstract":"Multi-agent reinforcement learning (MARL) algorithms often struggle to find strategies close to Pareto optimal Nash Equilibrium, owing largely to the lack of efficient exploration. The problem is exacerbated in sparse-reward settings, caused by the larger variance exhibited in policy learning. This paper introduces MESA, a novel meta-exploration method for cooperative multi-agent learning. It learns to explore by first identifying the agents' high-rewarding joint state-action subspace from training tasks and then learning a set of diverse exploration policies to\"cover\"the subspace. These trained exploration policies can be integrated with any off-policy MARL algorithm for test-time tasks. We first showcase MESA's advantage in a multi-step matrix game. Furthermore, experiments show that with learned exploration policies, MESA achieves significantly better performance in sparse-reward tasks in several multi-agent particle environments and multi-agent MuJoCo environments, and exhibits the ability to generalize to more challenging tasks at test time.","PeriodicalId":326727,"journal":{"name":"Adaptive Agents and Multi-Agent Systems","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Adaptive Agents and Multi-Agent Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5555/3635637.3663073","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
Multi-agent reinforcement learning (MARL) algorithms often struggle to find strategies close to Pareto optimal Nash Equilibrium, owing largely to the lack of efficient exploration. The problem is exacerbated in sparse-reward settings, caused by the larger variance exhibited in policy learning. This paper introduces MESA, a novel meta-exploration method for cooperative multi-agent learning. It learns to explore by first identifying the agents' high-rewarding joint state-action subspace from training tasks and then learning a set of diverse exploration policies to"cover"the subspace. These trained exploration policies can be integrated with any off-policy MARL algorithm for test-time tasks. We first showcase MESA's advantage in a multi-step matrix game. Furthermore, experiments show that with learned exploration policies, MESA achieves significantly better performance in sparse-reward tasks in several multi-agent particle environments and multi-agent MuJoCo environments, and exhibits the ability to generalize to more challenging tasks at test time.