{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T12:40:24Z","timestamp":1776775224844,"version":"3.51.2"},"reference-count":41,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Federal Ministry of Education and Research Bonn Office","doi-asserted-by":"publisher","award":["01DD20003"],"award-info":[{"award-number":["01DD20003"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.neucom.2025.131581","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T23:41:44Z","timestamp":1758584504000},"page":"131581","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Towards unbiased action value estimation in reinforcement learning"],"prefix":"10.1016","volume":"683","author":[{"given":"Yuan","family":"Xue","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3359-3255","authenticated-orcid":false,"given":"Daniel","family":"Kudenko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Megha","family":"Khosla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2025.131581_bib0005","author":"Ye"},{"key":"10.1016\/j.neucom.2025.131581_bib0010","author":"Micheli"},{"key":"10.1016\/j.neucom.2025.131581_bib0015","author":"Wang"},{"key":"10.1016\/j.neucom.2025.131581_bib0020","author":"Li"},{"key":"10.1016\/j.neucom.2025.131581_bib0025","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2025.131581_bib0030","author":"Kostrikov"},{"key":"10.1016\/j.neucom.2025.131581_bib0035","author":"Wang"},{"key":"10.1016\/j.neucom.2025.131581_bib0040","author":"He"},{"key":"10.1016\/j.neucom.2025.131581_bib0045","doi-asserted-by":"crossref","first-page":"3116","DOI":"10.1109\/LRA.2024.3363530","article-title":"Diffusion policies for out-of-distribution generalization in offline reinforcement learning","volume":"9","author":"Ada","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.neucom.2025.131581_bib0050","first-page":"23237","article-title":"Prioritizing samples in reinforcement learning with reducible loss","volume":"36","author":"Sujit","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2025.131581_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128836","article-title":"Improved exploration\u2013exploitation trade-off through adaptive prioritized experience replay","volume":"614","author":"Hassani","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2025.131581_bib0060","series-title":"International Conference on Machine Learning","first-page":"5639","article-title":"Curl: contrastive unsupervised representations for reinforcement learning","author":"Laskin","year":"2020"},{"key":"10.1016\/j.neucom.2025.131581_bib0065","author":"Yarats"},{"key":"10.1016\/j.neucom.2025.131581_bib0070","author":"Zhang"},{"key":"10.1016\/j.neucom.2025.131581_bib0075","author":"Schwarzer"},{"key":"10.1016\/j.neucom.2025.131581_bib0080","first-page":"4764","article-title":"Towards robust bisimulation metric learning","volume":"34","author":"Kemertas","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2025.131581_bib0085","first-page":"38786","article-title":"Efficient potential-based exploration in reinforcement learning using inverse dynamic bisimulation metric","volume":"36","author":"Wang","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2025.131581_bib0090","author":"Forbes"},{"key":"10.1016\/j.neucom.2025.131581_bib0095","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.future.2024.03.057","article-title":"Potential-based reward shaping using state\u2013space segmentation for efficiency in reinforcement learning","volume":"157","author":"Bal","year":"2024","journal-title":"Futur. Gener. Comput. Syst."},{"key":"10.1016\/j.neucom.2025.131581_bib0100","author":"Li"},{"key":"10.1016\/j.neucom.2025.131581_bib0105","author":"Ren"},{"key":"10.1016\/j.neucom.2025.131581_bib0110","author":"Park"},{"key":"10.1016\/j.neucom.2025.131581_bib0115","series-title":"Learning from delayed rewards","author":"Watkins","year":"1989"},{"key":"10.1016\/j.neucom.2025.131581_bib0120","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"nature"},{"key":"10.1016\/j.neucom.2025.131581_bib0125","series-title":"Proceedings of the Fourth Connectionist Models Summer School","first-page":"263","article-title":"Issues in using function approximation for reinforcement learning","author":"Thrun","year":"1993"},{"key":"10.1016\/j.neucom.2025.131581_bib0130","article-title":"Double q-learning","volume":"23","author":"Hasselt","year":"2010","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2025.131581_bib0135","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Deep reinforcement learning with double q-learning","author":"Van Hasselt","year":"2016"},{"key":"10.1016\/j.neucom.2025.131581_bib0140","series-title":"International Conference on Machine Learning","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"key":"10.1016\/j.neucom.2025.131581_bib0145","series-title":"International Conference on Machine Learning","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"Silver","year":"2014"},{"key":"10.1016\/j.neucom.2025.131581_bib0150","series-title":"International Conference on Machine Learning","first-page":"1861","article-title":"Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"10.1016\/j.neucom.2025.131581_bib0155","series-title":"International Conference on Machine Learning","first-page":"176","article-title":"Averaged-dqn: variance reduction and stabilization for deep reinforcement learning","author":"Anschel","year":"2017"},{"key":"10.1016\/j.neucom.2025.131581_bib0160","series-title":"Proceedings of the 7th European Workshop on Reinforcement Learning","first-page":"17","article-title":"Qv (lambda)-learning: a new on-policy reinforcement learning algrithm","author":"Wiering","year":"2005"},{"key":"10.1016\/j.neucom.2025.131581_bib0165","article-title":"Better exploration with optimistic actor critic","volume":"32","author":"Ciosek","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2025.131581_bib0170","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.127170","article-title":"Elastic step DQN: a novel multi-step algorithm to alleviate overestimation in deep q-networks","volume":"576","author":"Ly","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2025.131581_bib0175","series-title":"2020 International Joint Conference on Neural Networks (IJCNN)","first-page":"1","article-title":"The deep quality-value family of deep reinforcement learning algorithms","author":"Sabatelli","year":"2020"},{"key":"10.1016\/j.neucom.2025.131581_bib0180","series-title":"International Conference on Machine Learning","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"Wang","year":"2016"},{"key":"10.1016\/j.neucom.2025.131581_bib0185","series-title":"Introduction to Reinforcement Learning","volume":"vol. 135","author":"Sutton","year":"1998"},{"key":"10.1016\/j.neucom.2025.131581_bib0190","author":"Kaiser"},{"key":"10.1016\/j.neucom.2025.131581_bib0195","author":"Kostrikov"},{"key":"10.1016\/j.neucom.2025.131581_bib0200","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1023\/A:1007678930559","article-title":"Convergence results for single-step on-policy reinforcement-learning algorithms","volume":"38","author":"Singh","year":"2000","journal-title":"Mach. Learn."},{"key":"10.1016\/j.neucom.2025.131581_bib0205","article-title":"Convergence of stochastic iterative dynamic programming algorithms","volume":"6","author":"Jaakkola","year":"1993","journal-title":"Adv. Neural Inf. Process. Syst."}],"updated-by":[{"DOI":"10.1016\/j.neucom.2025.131581","type":"removal","label":"Removal","source":"publisher","updated":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T00:00:00Z","timestamp":1758153600000}}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231225022532?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231225022532?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T11:45:49Z","timestamp":1776771949000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231225022532"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":41,"alternative-id":["S0925231225022532"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2025.131581","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Towards unbiased action value estimation in reinforcement learning","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2025.131581","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"131581"}}