{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T06:19:22Z","timestamp":1787725162492,"version":"build-2784847793"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":[[2026,6]]},"DOI":"10.1109\/isit62367.2026.11654023","type":"proceedings-article","created":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T19:12:16Z","timestamp":1787685136000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["From Relative Entropy to Minimax: A Unified Framework for Coverage in MDPs"],"prefix":"10.1109","author":[{"given":"Xihe","family":"Gu","sequence":"first","affiliation":[{"name":"University of California, San Diego","place":["San Diego, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Urbashi","family":"Mitra","sequence":"additional","affiliation":[{"name":"University of Southern California","place":["Los Angeles, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tara","family":"Javidi","sequence":"additional","affiliation":[{"name":"University of California, San Diego","place":["San Diego, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5044","article-title":"Active coverage for pac reinforcement learning","volume-title":"The Thirty Sixth Annual Conference on Learning Theory","author":"Al-Marjani"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tsp.2025.3598253"},{"key":"ref3","article-title":"Global reinforcement learning: Beyond linear and convex rewards via submodular semi-gradient methods","author":"De Santi","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800030109"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE65448.2025.00285"},{"key":"ref6","first-page":"2681","article-title":"Provably efficient maximum entropy exploration","volume-title":"International Conference on Machine Learning","author":"Hazan"},{"key":"ref7","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"4870","article-title":"Reward-free exploration for reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Jin"},{"key":"ref9","first-page":"1094","article-title":"Learning to achieve goals","volume":"2","author":"Kaelbling","year":"1993","journal-title":"IJCAI"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2021.3090742"},{"key":"ref11","first-page":"865","article-title":"Adaptive reward-free exploration","volume-title":"Algorithmic Learning Theory","author":"Kaufmann","year":"2021"},{"key":"ref12","first-page":"1906","volume-title":"Efficient exploration via state marginal matching","author":"Lee","year":"2020"},{"key":"ref13","first-page":"22063","article-title":"What can online reinforcement learning with function approximation benefit from general coverage conditions?","volume-title":"International Conference on Machine Learning","author":"Liu"},{"key":"ref14","first-page":"7599","article-title":"Fast active learning for pure exploration in reinforcement learning","volume-title":"International Conference on Machine Learning","author":"M\u00e9nard"},{"issue":"250","key":"ref15","first-page":"1","article-title":"Convex reinforcement learning in finite trials","volume":"24","author":"Mutti","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2652"},{"key":"ref17","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning","author":"Schulman"},{"key":"ref18","first-page":"8687","article-title":"Adaptive sampling for estimating probability distributions","volume-title":"International Conference on Machine Learning","author":"Shekhar"},{"key":"ref19","first-page":"24535","article-title":"Adaptive sampling for minimax fair classification","volume":"34","author":"Shekhar","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","first-page":"2601","article-title":"Where do rewards come from","volume-title":"Proceedings of the annual conference of the cognitive science society","author":"Singh"},{"key":"ref21","first-page":"974","article-title":"Active exploration in markov decision processes","volume-title":"The 22nd International Conference on Artificial Intelligence and Statistics","author":"Tarbouriech"},{"key":"ref22","first-page":"1019","article-title":"Active model estimation in markov decision processes","volume-title":"Conference on Uncertainty in Artificial Intelligence","author":"Tarbouriech"},{"key":"ref23","first-page":"34161","article-title":"Fast rates for maximum entropy exploration","volume-title":"International Conference on Machine Learning","author":"Tiapkin"},{"key":"ref24","author":"Xia","journal-title":"Some results on max-min fairness for resource sharing"},{"key":"ref25","article-title":"The role of coverage in online reinforcement learning","author":"Xie","year":"2022"},{"key":"ref26","article-title":"The role of coverage in online reinforcement learning","author":"Xie","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17297"},{"key":"ref28","article-title":"On learning intrinsic rewards for policy gradient methods","volume":"31","author":"Zheng","year":"2018","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2026 IEEE International Symposium on Information Theory (ISIT)","location":"Guangzhou, China","start":{"date-parts":[[2026,6,28]]},"end":{"date-parts":[[2026,7,3]]}},"container-title":["2026 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11653602\/11653603\/11654023.pdf?arnumber=11654023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T05:26:52Z","timestamp":1787722012000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11654023\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/isit62367.2026.11654023","relation":{},"subject":[],"published":{"date-parts":[[2026,6]]}}}