{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:29:33Z","timestamp":1730204973607,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF)","doi-asserted-by":"publisher","award":["2020R1A2C2005709"],"award-info":[{"award-number":["2020R1A2C2005709"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003621","name":"Ministry of Science, ICT, and Future Planning","doi-asserted-by":"publisher","award":["2020R1A2C2005709"],"award-info":[{"award-number":["2020R1A2C2005709"]}],"id":[{"id":"10.13039\/501100003621","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,13]]},"DOI":"10.1109\/cdc49753.2023.10383458","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T13:38:36Z","timestamp":1705671516000},"page":"3402-3407","source":"Crossref","is-referenced-by-count":0,"title":["Scalable Robust Multi-Agent Reinforcement Learning for Model Uncertainty"],"prefix":"10.1109","author":[{"given":"Younkyung","family":"Jwa","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Gwangju Institute of Science and Technology (GIST),Gwangju,Korea"}]},{"given":"Minseon","family":"Gwak","sequence":"additional","affiliation":[{"name":"Pohang University of Science and Technology (POSTECH),Department of Electrical Engineering,Pohang,Korea"}]},{"given":"Jiin","family":"Kwak","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Graduate School, Ulsan National Institute of Science and Technology (UNIST),Ulsan,Korea"}]},{"given":"Chang Wook","family":"Ahn","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Gwangju Institute of Science and Technology (GIST),Gwangju,Korea"}]},{"given":"PooGyeon","family":"Park","sequence":"additional","affiliation":[{"name":"Pohang University of Science and Technology (POSTECH),Department of Electrical Engineering,Pohang,Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-021-0170-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992948"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207663"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2942014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561274"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2997896"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2021.3100898"},{"key":"ref8","first-page":"2074","article-title":"Scalable multi-agent reinforcement learning for networked systems with average reward","volume":"33","author":"Qu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","first-page":"21024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-021-0287-6"},{"key":"ref11","first-page":"6215","article-title":"Action robust reinforcement learning and applications in continuous control","volume-title":"International Conference on Machine Learning","author":"Tessler","year":"2019"},{"key":"ref12","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Pinto","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12115"},{"key":"ref14","first-page":"7193","article-title":"Online robust reinforcement learning with model uncertainty","volume":"34","author":"Wang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-020-0809-7"},{"key":"ref16","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref18","first-page":"10571","article-title":"Robust multi-agent reinforcement learning with model uncertainty","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-021-1021-0"},{"key":"ref20","first-page":"256","article-title":"Scalable reinforcement learning of localized policies for multi-agent networked systems","volume-title":"Learning for Dynamics and Control","author":"Qu","year":"2020"},{"key":"ref21","article-title":"Evolutionary population curriculum for scaling multi-agent reinforcement learning","author":"Long","year":"2020","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636344"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1887\/0750306645\/b877c23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11492"}],"event":{"name":"2023 62nd IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2023,12,13]]},"location":"Singapore, Singapore","end":{"date-parts":[[2023,12,15]]}},"container-title":["2023 62nd IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10383192\/10383193\/10383458.pdf?arnumber=10383458","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T11:58:59Z","timestamp":1706011139000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10383458\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/cdc49753.2023.10383458","relation":{},"subject":[],"published":{"date-parts":[[2023,12,13]]}}}