{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T13:21:33Z","timestamp":1788528093706,"version":"build-2803163510"},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114410","type":"journal-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:36:33Z","timestamp":1783697793000},"page":"114410","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PD","title":["Dynamic bias compensation in soft actor\u2013critic: A method for stable value estimation"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3869-3941","authenticated-orcid":false,"given":"Han","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5356-2427","authenticated-orcid":false,"given":"Wei","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8926-7833","authenticated-orcid":false,"given":"Yanyu","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4977-7577","authenticated-orcid":false,"given":"Lizhen","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114410_b1","unstructured":"T. Haarnoja, A. Zhou, P. Abbeel, S. Levine, Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor, in: Proceedings of the International Conference on Machine Learning, ICML, 2018, pp. 1861\u20131870."},{"key":"10.1016\/j.patcog.2026.114410_b2","unstructured":"S. Fujimoto, H. van Hoof, D. Meger, Addressing Function Approximation Error in Actor-Critic Methods, in: International Conference on Machine Learning, ICML, 2018, pp. 1587\u20131596."},{"key":"10.1016\/j.patcog.2026.114410_b3","article-title":"QFAE: Q-Function guided Action Exploration for offline deep reinforcement learning","volume":"158","author":"Wang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114410_b4","article-title":"Compact exploration for continuous action reinforcement learning","volume":"172","author":"Liu","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114410_b5","series-title":"Advances in Neural Information Processing Systems","first-page":"2613","article-title":"Double Q-learning","author":"van Hasselt","year":"2010"},{"issue":"5","key":"10.1016\/j.patcog.2026.114410_b6","doi-asserted-by":"crossref","first-page":"3935","DOI":"10.1109\/TPAMI.2025.3537087","article-title":"Distributional soft actor-critic with three refinements","volume":"47","author":"Duan","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114410_b7","article-title":"Deep learning-enhanced environment perception for autonomous driving: MDNet with CSP-DarkNet53","volume":"160","author":"Wang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114410_b8","article-title":"MPA-YOLO: Steel surface defect detection based on improved YOLOv8 framework","volume":"168","author":"Li","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114410_b9","article-title":"VLPA-CLIP: Video Language Prompting and Adapting CLIP for efficient video action recognition","volume":"168","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114410_b10","article-title":"Edge computing enabled video segmentation for real-time traffic monitoring in internet of vehicles","volume":"121","author":"Chen","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114410_b11","article-title":"Non-residual unrestricted pruned ultra-faster line detection for edge devices","volume":"137","author":"Lu","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114410_b12","article-title":"Optimizing reinforcement learning for large action spaces via generative models: Battery pattern selection","volume":"160","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114410_b13","article-title":"Deep reinforcement learning for efficient registration between intraoral-scan meshes and CT images","volume":"164","author":"Li","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114410_b14","series-title":"Proceedings of the ACM Workshop on Hot Topics in Networks","first-page":"50","article-title":"Resource management with deep reinforcement learning","author":"Mao","year":"2016"},{"key":"10.1016\/j.patcog.2026.114410_b15","article-title":"Joint task offloading, resource allocation, and service caching in mobile edge computing via soft actor-critic learning","author":"Liu","year":"2026","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.patcog.2026.114410_b16","series-title":"Proceedings of the International Conference on Distributed Artificial Intelligence","first-page":"58","article-title":"SAC-B: Soft actor-critic with bias for suppressing Q-value overestimation in off-policy reinforcement learning","author":"Wang","year":"2025"},{"issue":"1","key":"10.1016\/j.patcog.2026.114410_b17","article-title":"Deep reinforcement learning that matters","volume":"32","author":"Henderson","year":"2018","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.114410_b18","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1016\/j.future.2023.06.013","article-title":"EdgeSimPy: Python-based modeling and simulation of edge computing resource management policies","volume":"148","author":"Longo","year":"2023","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.patcog.2026.114410_b19","unstructured":"T.P. Lillicrap, J.J. Hunt, A. Pritzel, et al., Continuous Control with Deep Reinforcement Learning, in: International Conference on Learning Representations, ICLR, 2016."},{"key":"10.1016\/j.patcog.2026.114410_b20","unstructured":"G. Barth-Maron, M.W. Hoffman, D. Budden, W. Dabney, D. Horgan, A. Muldal, N. Heess, T. Lillicrap, Distributed Distributional Deterministic Policy Gradients, in: International Conference on Learning Representations, ICLR, 2018."},{"key":"10.1016\/j.patcog.2026.114410_b21","series-title":"Proceedings of the 60th Annual Allerton Conference on Communication, Control, and Computing","first-page":"1","article-title":"Suppressing overestimation in Q-learning through adversarial behaviors","author":"Lee","year":"2024"},{"key":"10.1016\/j.patcog.2026.114410_b22","series-title":"Advances in Neural Information Processing Systems","first-page":"24778","article-title":"Adaptive ensemble Q-learning: Minimizing estimation bias via error feedback","volume":"Vol. 34","author":"Wang","year":"2021"},{"key":"10.1016\/j.patcog.2026.114410_b23","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"},{"issue":"5","key":"10.1016\/j.patcog.2026.114410_b24","doi-asserted-by":"crossref","first-page":"638","DOI":"10.3390\/sym17050638","article-title":"Classification-based Q-value estimation for continuous actor-critic reinforcement learning","volume":"17","author":"Wang","year":"2025","journal-title":"Symmetry"},{"key":"10.1016\/j.patcog.2026.114410_b25","article-title":"Action adversarial robust reinforcement learning via Stackelberg game","volume":"165","author":"Liu","year":"2026","journal-title":"Pattern Recognit."},{"issue":"6","key":"10.1016\/j.patcog.2026.114410_b26","doi-asserted-by":"crossref","first-page":"7112","DOI":"10.1109\/TPAMI.2026.3664855","article-title":"A generic competitive-cooperative actor-critic framework for deep reinforcement learning","volume":"48","author":"Xu","year":"2026","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114410_b27","unstructured":"X. Chen, C. Wang, Z. Zhou, K. Ross, Randomized Ensembled Double Q-Learning: Learning Fast Without a Model, in: International Conference on Learning Representations, ICLR, 2021."},{"key":"10.1016\/j.patcog.2026.114410_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.adhoc.2024.103646","article-title":"RL-based mobile edge computing scheme for high reliability low latency services in UAV-aided IIoT networks","volume":"166","author":"Sweidan","year":"2025","journal-title":"Ad Hoc Netw."},{"issue":"1","key":"10.1016\/j.patcog.2026.114410_b29","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1109\/TSC.2024.3489443","article-title":"Multi-objective deep reinforcement learning for function offloading in serverless edge computing","volume":"18","author":"Yang","year":"2025","journal-title":"IEEE Trans. Serv. Comput."},{"issue":"2","key":"10.1016\/j.patcog.2026.114410_b30","doi-asserted-by":"crossref","first-page":"2035","DOI":"10.1109\/JIOT.2025.3627985","article-title":"Energy-efficient microservice orchestration for latency-sensitive applications in edge computing: A reinforcement learning approach","volume":"13","author":"Zhang","year":"2026","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.patcog.2026.114410_b31","article-title":"Deep-reinforcement-learning-based task offloading and resource allocation in mobile edge computing network with heterogeneous tasks","author":"Li","year":"2025","journal-title":"IEEE Internet Things J."},{"issue":"1","key":"10.1016\/j.patcog.2026.114410_b32","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1109\/TSC.2025.3622026","article-title":"FLISC3: Federated learning-oriented resource optimization in ISCC-enabled edge collaborative networks","volume":"19","author":"Liu","year":"2026","journal-title":"IEEE Trans. Serv. Comput."},{"issue":"2","key":"10.1016\/j.patcog.2026.114410_b33","doi-asserted-by":"crossref","first-page":"365","DOI":"10.3390\/pr14020365","article-title":"Hierarchical soft actor-critic agent with automatic entropy, twin critics, and curriculum learning for the autonomy of rock-breaking machinery in mining comminution processes","volume":"14","author":"Chen","year":"2026","journal-title":"Processes"},{"key":"10.1016\/j.patcog.2026.114410_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.simpa.2020.100022","article-title":"dm_control: Software and tasks for continuous control","volume":"6","author":"Tunyasuvunakool","year":"2020","journal-title":"Softw. Impacts"},{"key":"10.1016\/j.patcog.2026.114410_b35","series-title":"Proceedings of the 32nd International Conference on Machine Learning","first-page":"1889","article-title":"Trust region policy optimization","volume":"vol. 37","author":"Schulman","year":"2015"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326013750?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326013750?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T12:52:46Z","timestamp":1788526366000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326013750"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":35,"alternative-id":["S0031320326013750"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114410","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Dynamic bias compensation in soft actor\u2013critic: A method for stable value estimation","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114410","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114410"}}