{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T06:13:39Z","timestamp":1768976019669,"version":"3.49.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001381","name":"Consejo Nacional de Humaninades Ciencias y Tecnolog\u00edas (CONAHCyT), Cardiff University, National Research Foundation, Singapore, under its AI Singapore Program","doi-asserted-by":"publisher","award":["AISG2-RP-2020-019"],"award-info":[{"award-number":["AISG2-RP-2020-019"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/X018962\/1"],"award-info":[{"award-number":["EP\/X018962\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Singapore Management University through the Jubilee Technology Fellowship"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tnnls.2023.3325633","type":"journal-article","created":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T14:12:26Z","timestamp":1698761546000},"page":"419-432","source":"Crossref","is-referenced-by-count":5,"title":["Deep Reinforcement Learning With Explicit Context Representation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8397-3083","authenticated-orcid":false,"given":"Francisco","family":"Munguia-Galeano","sequence":"first","affiliation":[{"name":"School of Engineering, Cardiff University, Cardiff, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0378-4069","authenticated-orcid":false,"given":"Ah-Hwee","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Bras Basah, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8968-9902","authenticated-orcid":false,"given":"Ze","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Engineering, Cardiff University, Cardiff, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-020-05938-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3207346"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref5","first-page":"11501","article-title":"Conservative data sharing for multi-task offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3059912"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2790981"},{"issue":"124","key":"ref8","first-page":"1","article-title":"Deep exploration via randomized value functions","volume":"20","author":"Osband","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref9","first-page":"1","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Bellemare"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2806087"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref13","first-page":"3138","article-title":"Sample-efficient imitation learning via generative adversarial nets","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Blond\u00e9"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1023\/A:1015008417172"},{"key":"ref15","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref16","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-020-0087-8"},{"key":"ref18","volume-title":"Stable Baselines","author":"Hill","year":"2018"},{"key":"ref19","first-page":"1","article-title":"Double Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Hasselt"},{"key":"ref20","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2021.06.021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3053348"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927869"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3209154"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2805379"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2019.8914266"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115680"},{"key":"ref29","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","volume-title":"Proc. 28th Int. Conf. Mach. Learn. (ICML)","author":"Deisenroth"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2020.3006520"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1002\/int.23029"},{"issue":"7","key":"ref33","first-page":"1","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"Taylor","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS48487.2020.00015"},{"key":"ref35","article-title":"Contextual Markov decision processes","author":"Hallak","year":"2015","journal-title":"arXiv:1502.02259"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05984-x"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2021.3100291"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-33-4084-8_12"},{"key":"ref39","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref40","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref41","article-title":"Contextualize me\u2014The case for context in reinforcement learning","author":"Benjamins","year":"2022","journal-title":"arXiv:2202.04500"},{"key":"ref42","article-title":"CARL: A benchmark for contextual and adaptive reinforcement learning","author":"Benjamins","year":"2021","journal-title":"arXiv:2110.02102"},{"key":"ref43","first-page":"9767","article-title":"Multi-task reinforcement learning with context-based representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sodhani"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2327636"},{"issue":"2","key":"ref45","first-page":"67","volume-title":"The Theory of Affordances","volume":"1","author":"Gibson","year":"1977"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2017.1394912"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2430335"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2690910"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2543839"},{"key":"ref50","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10832116\/10302322.pdf?arnumber=10302322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:38:54Z","timestamp":1764959934000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10302322\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":50,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3325633","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}