{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:30:39Z","timestamp":1770845439741,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"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":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11342671","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"5655-5660","source":"Crossref","is-referenced-by-count":0,"title":["Learning What Matters Now: A Dual-Critic Context-Aware RL Framework for Priority-Driven Information Gain"],"prefix":"10.1109","author":[{"given":"Dimitris","family":"Panagopoulos","sequence":"first","affiliation":[{"name":"Cranfield University,Faculty of Engineering and Applied Science,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adolfo","family":"Perrusqu\u00eda","sequence":"additional","affiliation":[{"name":"Cranfield University,Faculty of Engineering and Applied Science,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weisi","family":"Guo","sequence":"additional","affiliation":[{"name":"Cranfield University,Faculty of Engineering and Applied Science,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2024.1527095"},{"key":"ref3","article-title":"Maxinforl: Boosting exploration in reinforcement learning through information gain maximization","author":"Sukhija","year":"2024"},{"key":"ref4","first-page":"28575","article-title":"Regret bounds for information-directed reinforcement learning","volume":"35","author":"Hao","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SMC54092.2024.10831125"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/HST56032.2022.10025434"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-024-1512-6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.70322\/dav.2024.10012"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref10","article-title":"Boltzmann exploration done right","volume":"30","author":"Cesa-Bianchi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"An empirical evaluation of thompson sampling","volume":"24","author":"Chapelle","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref13","article-title":"Unifying count-based exploration and intrinsic motivation","volume":"29","author":"Bellemare","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Surprise-based intrinsic motivation for deep reinforcement learning","author":"Achiam","year":"2017","journal-title":"arXiv preprint arXiv:1703.01732"},{"key":"ref15","article-title":"Exploration by random network distillation","author":"Burda","year":"2018"},{"key":"ref16","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"International conference on machine learning","author":"Finn"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_5781"},{"key":"ref19","article-title":"Reinforcement learning in presence of discrete markovian context evolution","author":"Ren","year":"2022"},{"key":"ref20","first-page":"5757","article-title":"Context-aware dynamics model for generalization in model-based reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Lee"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2017.1663"},{"key":"ref22","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11342671.pdf?arnumber=11342671","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:50:46Z","timestamp":1770843046000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342671\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11342671","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}