{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T02:27:29Z","timestamp":1730341649803,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T00:00:00Z","timestamp":1685491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T00:00:00Z","timestamp":1685491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,31]]},"DOI":"10.23919\/acc55779.2023.10156072","type":"proceedings-article","created":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T13:48:03Z","timestamp":1688392083000},"page":"3977-3982","source":"Crossref","is-referenced-by-count":1,"title":["Scalable Multi-Agent Reinforcement Learning with General Utilities"],"prefix":"10.23919","author":[{"given":"Donghao","family":"Ying","sequence":"first","affiliation":[{"name":"University of California at Berkeley,Department of Industrial Engineering and Operations Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Ding","sequence":"additional","affiliation":[{"name":"University of California at Berkeley,Department of Industrial Engineering and Operations Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alec","family":"Koppel","sequence":"additional","affiliation":[{"name":"J.P. Morgan AI Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javad","family":"Lavaei","sequence":"additional","affiliation":[{"name":"University of California at Berkeley,Department of Industrial Engineering and Operations Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1145\/1015330.1015430"},{"year":"2018","author":"Eysenbach","article-title":"Diversity is all you need: Learning skills without a reward function","key":"ref2"},{"key":"ref3","first-page":"2681","article-title":"Provably efficient maximum entropy exploration","volume-title":"International Conference on Machine Learning","author":"Hazan"},{"year":"2019","author":"Lee","article-title":"Efficient exploration via state marginal matching","key":"ref4"},{"key":"ref5","first-page":"4572","article-title":"Variational policy gradient method for reinforcement learning with general utilities","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","article-title":"Reward is enough for convex mdps","volume":"34","author":"Zahavy","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1016\/j.arcontrol.2017.09.002"},{"key":"ref8","first-page":"3040","article-title":"Social influence as intrinsic motivation for multi-agent deep reinforcement learning","volume-title":"International conference on machine learning","author":"Jaques"},{"key":"ref9","first-page":"451","article-title":"Stock trading system using reinforcement learning with cooperative agents","volume-title":"Proceedings of the Nineteenth International Conference on Machine Learning","author":"Lee"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1177\/0278364915581863"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1007\/s11134-019-09598-y"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1609\/aaai.v36i8.20887"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1016\/S0005-1098(00)00050-9"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1287\/opre.2021.2226"},{"key":"ref15","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"year":"2021","author":"Alfano","article-title":"Dimension-free rates for natural policy gradient in multi-agent reinforcement learning","key":"ref16"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1515\/9783110250329"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1287\/educ.2013.0119"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1017\/CBO9780511807213"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1145\/1024916.1024920"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.23919\/ACC55779.2023.10156072"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1023\/A:1022633531479"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/tit.2021.3120096"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1007\/s10994-013-5368-1"},{"key":"ref25","first-page":"278","article-title":"Learning to coordinate in multi-agent systems: A coordinated actor-critic algorithm and finite-time guarantees","volume-title":"Learning for Dynamics and Control Conference","author":"Zeng"},{"key":"ref26","first-page":"2228","article-title":"On the convergence and sample efficiency of variance-reduced policy gradient method","volume":"34","author":"Zhang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1609\/aaai.v37i9.26299"}],"event":{"name":"2023 American Control Conference (ACC)","start":{"date-parts":[[2023,5,31]]},"location":"San Diego, CA, USA","end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10155646\/10155787\/10156072.pdf?arnumber=10156072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T22:51:44Z","timestamp":1710370304000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10156072\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,31]]},"references-count":27,"URL":"https:\/\/doi.org\/10.23919\/acc55779.2023.10156072","relation":{},"subject":[],"published":{"date-parts":[[2023,5,31]]}}}