DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jeon, Jeewon | ko |
dc.contributor.author | Kim, Woojun | ko |
dc.contributor.author | Jung, Whiyoung | ko |
dc.contributor.author | Sung, Youngchul | ko |
dc.date.accessioned | 2023-09-19T12:00:22Z | - |
dc.date.available | 2023-09-19T12:00:22Z | - |
dc.date.created | 2023-09-19 | - |
dc.date.issued | 2022-07 | - |
dc.identifier.citation | 39th International Conference on Machine Learning, ICML 2022, pp.10041 - 10052 | - |
dc.identifier.issn | 2640-3498 | - |
dc.identifier.uri | http://hdl.handle.net/10203/312777 | - |
dc.description.abstract | In this paper, we consider cooperative multi-agent reinforcement learning (MARL) with sparse reward. To tackle this problem, we propose a novel method named MASER: MARL with subgoals generated from experience replay buffer. Under the widely-used assumption of centralized training with decentralized execution and consistent Q-value decomposition for MARL, MASER automatically generates proper subgoals for multiple agents from the experience replay buffer by considering both individual Q-value and total Q-value. Then, MASER designs individual intrinsic reward for each agent based on actionable representation relevant to Q-learning so that the agents reach their subgoals while maximizing the joint action value. Numerical results show that MASER significantly outperforms StarCraft II micromanagement benchmark compared to other state-of-the-art MARL algorithms. | - |
dc.language | English | - |
dc.publisher | ML Research Press | - |
dc.title | MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer | - |
dc.type | Conference | - |
dc.identifier.wosid | 000900064900002 | - |
dc.identifier.scopusid | 2-s2.0-85163097460 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 10041 | - |
dc.citation.endingpage | 10052 | - |
dc.citation.publicationname | 39th International Conference on Machine Learning, ICML 2022 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Baltimore, MD | - |
dc.contributor.localauthor | Sung, Youngchul | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.