{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T05:40:31Z","timestamp":1756273231123,"version":"3.44.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"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":[[2025,5,26]]},"DOI":"10.23919\/wiopt66569.2025.11123313","type":"proceedings-article","created":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T19:04:05Z","timestamp":1756235045000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Tabular and Deep Reinforcement Learning for Gittins Index"],"prefix":"10.23919","author":[{"given":"Harshit","family":"Dhankhar","sequence":"first","affiliation":[{"name":"IIT Patna,Department of Mathematics,Patna,India"}]},{"given":"Kshitij","family":"Mishra","sequence":"additional","affiliation":[{"name":"Computer Systems Group, IIIT Hyderabad,Hyderabad,Telegana"}]},{"given":"Tejas","family":"Bodas","sequence":"additional","affiliation":[{"name":"Computer Systems Group, IIIT Hyderabad,Hyderabad,Telegana"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11134-009-9141-x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11134-023-09888-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11134-024-09902-5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s00186-024-00877-w"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012999361974"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2023.3333402"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110186"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8277-6"},{"volume-title":"Tabular and deep reinforcement learning for gittins index","year":"2024","author":"Dhankhar","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50034-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-013-1523-0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11134-023-09875-x"},{"key":"ref14","article-title":"A dynamic allocation index for the sequential design of experiments","volume-title":"Progress in Statistics","author":"Gittins","year":"1974"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1979.tb01068.x"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/9780470980033"},{"key":"ref17","first-page":"1289","article-title":"Reinforcement learning algorithms for regret minimization in structured markov decision processes: (extended abstract)","volume-title":"Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems, AAMAS \u201916","author":"Prabuchandran","year":"2016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref20","first-page":"176","article-title":"Deep q-learning with whittle index for contextual restless bandits: Application to email recommender systems","volume-title":"Proceedings of the 6th Northern Lights Deep Learning Conference (NLDL)","author":"El Mimouni","year":"2025"},{"key":"ref21","first-page":"28734","article-title":"Deeptop: Deep threshold-optimal policy for mdps and rmabs","volume":"35","author":"Nakhleh","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-2361-4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3512798.3512816"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3670686"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3306309.3306321"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3579342.3579344"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3428328"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3452006"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1214\/aoap\/1177005207"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1214\/15-AAP1137"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.2307\/3214547"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1980.tb01111.x"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2307\/3214163"}],"event":{"name":"2025 23rd International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)","start":{"date-parts":[[2025,5,26]]},"location":"Linkoping, Sweden","end":{"date-parts":[[2025,5,29]]}},"container-title":["2025 23rd International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11123177\/11123184\/11123313.pdf?arnumber=11123313","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T05:15:08Z","timestamp":1756271708000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11123313\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,26]]},"references-count":33,"URL":"https:\/\/doi.org\/10.23919\/wiopt66569.2025.11123313","relation":{},"subject":[],"published":{"date-parts":[[2025,5,26]]}}}