{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T08:09:20Z","timestamp":1763194160922,"version":"3.45.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11229044","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Value of Information-Enhanced Exploration in Bootstrapped DQN"],"prefix":"10.1109","author":[{"given":"Stergios","family":"Plataniotis","sequence":"first","affiliation":[{"name":"Technical University of Crete,Chania,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charilaos","family":"Akasiadis","sequence":"additional","affiliation":[{"name":"Technical University of Crete & NCSR \"Demokritos\",Chania,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgios","family":"Chalkiadakis","sequence":"additional","affiliation":[{"name":"Technical University of Crete,Chania,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/2200000071"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref6","first-page":"4033","article-title":"Deep exploration via Bootstrapped DQN","volume-title":"NIPS","author":"Osband"},{"key":"ref7","first-page":"5062","article-title":"Self-supervised exploration via disagreement","volume-title":"ICML","author":"Pathak"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6036"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3236361"},{"key":"ref10","first-page":"761","article-title":"Bayesian q-learning","volume-title":"AAAI","author":"Dearden"},{"key":"ref11","first-page":"150","article-title":"Model based bayesian exploration","volume-title":"UAI","author":"Dearden"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/860575.860689"},{"key":"ref13","first-page":"417","article-title":"Decentralized bayesian reinforcement learning for online agent collaboration","volume-title":"AAMAS","author":"Teacy"},{"volume-title":"Artificial Intelligence: A Modern Approach","year":"2020","author":"Russell","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107446984"},{"article-title":"The curse of diversity in ensemble-based exploration","volume-title":"ICLR","author":"Lin","key":"ref17"},{"article-title":"Information-directed exploration for deep reinforcement learning","volume-title":"ICLR","author":"Nikolov","key":"ref18"},{"key":"ref19","first-page":"1583","article-title":"Learning to optimize via information-directed sampling","volume-title":"NIPS","author":"Russo"},{"article-title":"Ucb exploration via q-ensembles","year":"2017","author":"Chen","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2009.01.016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703732"},{"key":"ref26","first-page":"6131","article-title":"Sunrise: A simple unified framework for ensemble learning in deep reinforcement learning","volume-title":"ICML","author":"Lee"},{"key":"ref27","first-page":"1479","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"NIPS, ser. NIPS\u201916","author":"Bellemare"},{"key":"ref28","first-page":"1","article-title":"Exploration by random network distillation","volume-title":"ICLR","author":"Burda"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"ICLR","author":"Kingma","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"article-title":"Gymnasium: A standard interface for reinforcement learning environments","year":"2024","author":"Towers","key":"ref31"},{"key":"ref32","first-page":"11 720","article-title":"Diversity and generalization in neural network ensembles","volume-title":"AISTATS","author":"Ortega"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11229044.pdf?arnumber=11229044","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T08:04:49Z","timestamp":1763193889000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11229044\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11229044","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}