{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T13:04:45Z","timestamp":1782133485264,"version":"3.54.5"},"reference-count":29,"publisher":"IEEE","funder":[{"DOI":"10.13039\/100000001","name":"National Science of Foundation (NSF)","doi-asserted-by":"publisher","award":["Cns-1544782,Cns-2027884,SES-1541164"],"award-info":[{"award-number":["Cns-1544782,Cns-2027884,SES-1541164"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office (ARO)","doi-asserted-by":"publisher","award":["W911NF-19-1-0041"],"award-info":[{"award-number":["W911NF-19-1-0041"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"Department of Energy (DOE)","doi-asserted-by":"publisher","award":["DE-NE0008986"],"award-info":[{"award-number":["DE-NE0008986"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,3,24]]},"DOI":"10.1109\/ciss50987.2021.9400319","type":"proceedings-article","created":{"date-parts":[[2021,4,22]],"date-time":"2021-04-22T03:11:36Z","timestamp":1619061096000},"page":"1-6","source":"Crossref","is-referenced-by-count":9,"title":["Blackwell Online Learning for Markov Decision Processes"],"prefix":"10.1109","author":[{"given":"Tao","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanze","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quanyan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.2140\/pjm.1956.6.1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3934\/jdg.2014.1.181"},{"key":"ref12","first-page":"27","article-title":"Blackwell Approachability and No-Regret Learning are Equivalent","volume":"19","author":"abernethy","year":"2011","journal-title":"Proceedings of the 24th Annual Conference on Learning Theory"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1090.0397"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1090.0396"},{"key":"ref15","first-page":"7216","article-title":"Non-stationary markov decision processes, a worst-case approach using model-based reinforcement learning","volume":"32","author":"lecarpentier","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143872"},{"key":"ref17","first-page":"593","article-title":"Combining No-Regret and Q-Learning","author":"kash","year":"2020","journal-title":"Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems AAMAS ‘20"},{"key":"ref18","article-title":"Neuro-dynamic programming","author":"bertsekas","year":"1996","journal-title":"Optimization and Neural Computation Series"},{"key":"ref19","author":"li","year":"2020","journal-title":"Blackwell online learning for markov decision processes"},{"key":"ref28","author":"fudenberg","year":"1998","journal-title":"The Theory of Learning in Games"},{"key":"ref4","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1214\/11-SSY056"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1954-09848-8"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref29","first-page":"1641","article-title":"Cyclic Equilibria in Markov Games","author":"zinkevich","year":"2006","journal-title":"Advances in Neural Information Processing Systems 18"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1023\/A:1022632907294","article-title":"Q-Learning","volume":"8","author":"dayan","year":"1992","journal-title":"Machine Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2019.8918816"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1561\/2200000018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/S036301299731669X"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1111\/1468-0262.00153"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1561\/2200000068"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0899-8256(03)00178-7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012904439301"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1007\/978-93-86279-38-5","volume":"48","author":"borkar","year":"2008","journal-title":"Stochastic Approximation A Dynamical Systems Viewpoint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927542"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1060.0213"}],"event":{"name":"2021 55th Annual Conference on Information Sciences and Systems (CISS)","location":"Baltimore, MD, USA","start":{"date-parts":[[2021,3,24]]},"end":{"date-parts":[[2021,3,26]]}},"container-title":["2021 55th Annual Conference on Information Sciences and Systems (CISS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9400188\/9400208\/09400319.pdf?arnumber=9400319","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T21:35:49Z","timestamp":1643319349000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9400319\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,24]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/ciss50987.2021.9400319","relation":{},"subject":[],"published":{"date-parts":[[2021,3,24]]}}}