{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:14:54Z","timestamp":1771024494132,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,11,4]],"date-time":"2021-11-04T00:00:00Z","timestamp":1635984000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,4]],"date-time":"2021-11-04T00:00:00Z","timestamp":1635984000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,4]],"date-time":"2021-11-04T00:00:00Z","timestamp":1635984000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"U.S. Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-19-1-2131"],"award-info":[{"award-number":["N00014-19-1-2131"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-20-1-0265"],"award-info":[{"award-number":["W911NF-20-1-0265"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF CAREER","doi-asserted-by":"publisher","award":["2044993"],"award-info":[{"award-number":["2044993"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,11,4]]},"DOI":"10.1109\/mrs50823.2021.9620607","type":"proceedings-article","created":{"date-parts":[[2021,12,7]],"date-time":"2021-12-07T20:49:53Z","timestamp":1638910193000},"page":"155-163","source":"Crossref","is-referenced-by-count":10,"title":["Local Advantage Actor-Critic for Robust Multi-Agent Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yuchen","family":"Xiao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueguang","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Amato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref32","first-page":"344","article-title":"Improved memory-bounded dynamic programming for decentralized pomdps","author":"seuken","year":"0","journal-title":"Proceedings of the Conference on Uncertainty in Artificial Intelligence"},{"key":"ref31","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","author":"omidshafiei","year":"0","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref30","first-page":"1","article-title":"Expected policy gradients for reinforcement learning","volume":"21","author":"ciosek","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"},{"key":"ref12","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref13","article-title":"Weighted qmix: Expanding monotonic value function factorisation","author":"rashid","year":"0","journal-title":"Proceedings of the conference on Neural Information Processing Systems"},{"key":"ref14","first-page":"7611","article-title":"Maven: Multi-agent variational exploration","author":"mahajan","year":"0","journal-title":"Proceedings of the conference on Neural Information Processing Systems"},{"key":"ref15","article-title":"Roma: Multi-agent reinforcement learning with emergent roles","author":"wang","year":"2020","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11794","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2018","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref17","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"0","journal-title":"Proceedings of the conference on Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref19","author":"wang","year":"2020","journal-title":"Shapley q-value A local reward approach to solve global reward games"},{"key":"ref28","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"0","journal-title":"Proceedings of the conference on Neural Information Processing Systems"},{"key":"ref4","author":"alon","year":"2020","journal-title":"Multi-agent reinforcement learning for unmanned aerial vehicle coordination by multi-critic policy gradient optimization"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196684"},{"key":"ref6","author":"samvelyan","year":"2019","journal-title":"The StarCraft Multi-Agent Challenge"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref29","article-title":"Contrasting centralized and decentralized critics in multi-agent reinforcement learning","author":"lyu","year":"0","journal-title":"Proceedings of the International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref8","article-title":"Emergent coordination through competition","author":"liu","year":"0","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"ref7","article-title":"Emergent tool use from multi -agent autocurricula","author":"baker","year":"0","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00297"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref1","article-title":"Learning to improve multi-robot hallway navigation","author":"park","year":"2020","journal-title":"Proceedings of the Conference on Robot Learning"},{"key":"ref20","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume":"97","author":"iqbal","year":"0","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1142\/S0219525901000188"},{"key":"ref21","article-title":"Liir: Learning individual intrinsic reward in multi -agent reinforcement learning","author":"du","year":"0","journal-title":"Proceedings of the Conference on Neural Information Processing Systems 2019"},{"key":"ref24","article-title":"DOP: Off-policy multi-agent decomposed policy gradients","author":"wang","year":"0","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"ref23","article-title":"Value-decomposition multi-agent actor-critics","author":"su","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref25","article-title":"Cm3: Cooperative multi-goal multi-stage multi-agent reinforcement learning","author":"yang","year":"0","journal-title":"Proceedings of the International Conference on Learning Representations"}],"event":{"name":"2021 International Symposium on Multi-Robot and Multi-Agent Systems (MRS)","location":"Cambridge, United Kingdom","start":{"date-parts":[[2021,11,4]]},"end":{"date-parts":[[2021,11,5]]}},"container-title":["2021 International Symposium on Multi-Robot and Multi-Agent Systems (MRS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9620207\/9620540\/09620607.pdf?arnumber=9620607","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T15:40:13Z","timestamp":1673970013000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9620607\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,4]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/mrs50823.2021.9620607","relation":{},"subject":[],"published":{"date-parts":[[2021,11,4]]}}}