{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T21:01:06Z","timestamp":1774990866976,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"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":[[2019,9]]},"DOI":"10.1109\/allerton.2019.8919864","type":"proceedings-article","created":{"date-parts":[[2019,12,6]],"date-time":"2019-12-06T04:23:39Z","timestamp":1575606219000},"page":"726-733","source":"Crossref","is-referenced-by-count":1,"title":["Learning to Control in Metric Space with Optimal Regret"],"prefix":"10.1109","author":[{"given":"Chengzhuo","family":"Ni","sequence":"first","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin F.","family":"Yang","sequence":"additional","affiliation":[{"name":"UCLA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengdi","family":"Wang","sequence":"additional","affiliation":[{"name":"Princeton University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1563","article-title":"Near-optimal regret bounds for reinforcement learning","author":"jaksch","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref11","first-page":"125","volume":"558","author":"lattimore","year":"2014","journal-title":"Near-optimal pac bounds for discounted mdps"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2014.09.029"},{"key":"ref13","article-title":"The sample-complexity of general reinforcement learning","author":"lattimore","year":"2013","journal-title":"Proceedings of the 30th International Conference on Machine Learning"},{"key":"ref14","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref15","first-page":"8888","article-title":"Exploration in structured reinforcement learning","author":"ok","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-75225-7_30"},{"key":"ref17","first-page":"1763","article-title":"Online regret bounds for undiscounted continuous reinforcement learning","author":"ortner","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"On lower bounds for regret in reinforcement learning","author":"osband","year":"2016","journal-title":"arXiv preprint arXiv 1608 02732"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390251"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v24i1.7751","article-title":"Using bisimulation for policy transfer in mdps","author":"castro","year":"2010","journal-title":"Twenty-Fourth AAAI Conference on Artificial Intelligence"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1977.24"},{"key":"ref3","volume":"1","author":"bertsekas","year":"1995","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref6","first-page":"4192","article-title":"Regret bounds for robust adaptive control of the linear quadratic regulator","author":"dean","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref5","first-page":"2818","article-title":"Sample complexity of episodic fixed-horizon reinforcement learning","author":"dann","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"162","article-title":"Metrics for finite markov decision processes","author":"ferns","year":"2004","journal-title":"Proceedings of the 20th conference on Uncertainty in artificial intelligence"},{"key":"ref7","article-title":"Methods for computing state similarity in markov decision processes","author":"ferns","year":"2012","journal-title":"arXiv preprint arXiv 1206 6836"},{"key":"ref2","article-title":"Minimax regret bounds for reinforcement learning","author":"azar","year":"2017","journal-title":"arXiv preprint arXiv 1703 08337"},{"key":"ref9","article-title":"Metrics for markov decision processes with infinite state spaces","author":"ferns","year":"2012","journal-title":"arXiv preprint arXiv 1207 1386"},{"key":"ref1","first-page":"1184","article-title":"Optimistic posterior sampling for reinforcement learning: worst-case regret bounds","author":"agrawal","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v27i1.8678","article-title":"Pac optimal exploration in continuous space markov decision processes","author":"pazis","year":"2013","journal-title":"Twenty-Seventh AAAI Conference on Artificial Intelligence"},{"key":"ref22","first-page":"361","article-title":"Reinforcement learning with soft state aggregation","author":"singh","year":"1995","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Near-optimal time and sample complexities for for solving discounted markov decision process with a generative model","author":"sidford","year":"2018","journal-title":"arXiv preprint arXiv 1806 01492"},{"key":"ref24","article-title":"Computing probabilistic bisimilarity distances via policy iteration","author":"tang","year":"2016","journal-title":"27th International Conference on Concurrency Theory (CONCUR 2016)"},{"key":"ref23","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref26","first-page":"6995","article-title":"Sample-optimal parametric q-learning using linearly additive features","author":"yang","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2016.0826"}],"event":{"name":"2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","location":"Monticello, IL, USA","start":{"date-parts":[[2019,9,24]]},"end":{"date-parts":[[2019,9,27]]}},"container-title":["2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8911248\/8919648\/08919864.pdf?arnumber=8919864","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T19:52:03Z","timestamp":1774986723000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8919864\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/allerton.2019.8919864","relation":{},"subject":[],"published":{"date-parts":[[2019,9]]}}}