{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T03:57:46Z","timestamp":1781150266771,"version":"3.54.1"},"reference-count":29,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100005374","name":"Nanjing University of Posts and Telecommunications","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62506172"],"award-info":[{"award-number":["62506172"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276142"],"award-info":[{"award-number":["62276142"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202240"],"award-info":[{"award-number":["62202240"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206133"],"award-info":[{"award-number":["62206133"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2242025K30024"],"award-info":[{"award-number":["2242025K30024"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.neunet.2026.108896","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T03:52:28Z","timestamp":1774583548000},"page":"108896","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Bellman error centering"],"prefix":"10.1016","volume":"201","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8757-1767","authenticated-orcid":false,"given":"Xingguo","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinguo","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5499-4965","authenticated-orcid":false,"given":"Chao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shangdong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.neunet.2026.108896_bib0001","doi-asserted-by":"crossref","first-page":"681","DOI":"10.1137\/S0363012999361974","article-title":"Learning algorithms for Markov decision processes with average cost","volume":"40","author":"Abounadi","year":"2001","journal-title":"SIAM Journal on Control and Optimization"},{"key":"10.1016\/j.neunet.2026.108896_bib0002","series-title":"Proceedings of the 12th international conference machine learning","first-page":"30","article-title":"Residual algorithms: Reinforcement learning with function approximation","author":"Baird","year":"1995"},{"issue":"5","key":"10.1016\/j.neunet.2026.108896_bib0003","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/S0167-6911(97)90015-3","article-title":"Stochastic approximation with two time scales","volume":"29","author":"Borkar","year":"1997","journal-title":"Systems & Control Letters"},{"issue":"2","key":"10.1016\/j.neunet.2026.108896_bib0004","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1137\/S0363012997331639","article-title":"The ODE method for convergence of stochastic approximation and reinforcement learning","volume":"38","author":"Borkar","year":"2000","journal-title":"SIAM Journal on Control and Optimization"},{"key":"10.1016\/j.neunet.2026.108896_bib0005","series-title":"International conference on machine learning","first-page":"3676","article-title":"Grounding large language models in interactive environments with online reinforcement learning","author":"Carta","year":"2023"},{"key":"10.1016\/j.neunet.2026.108896_bib0006","series-title":"Uncertainty in artificial intelligence","first-page":"303","article-title":"Modified retrace for off-policy temporal difference learning","author":"Chen","year":"2023"},{"issue":"18","key":"10.1016\/j.neunet.2026.108896_bib0007","doi-asserted-by":"crossref","first-page":"2930","DOI":"10.3390\/math12182930","article-title":"On convergence rate of MRetrace","volume":"12","author":"Chen","year":"2024","journal-title":"Mathematics"},{"issue":"6","key":"10.1016\/j.neunet.2026.108896_bib0008","first-page":"1246","article-title":"A survey of reinforcement learning algorithms from a fixed point perspective","volume":"46","author":"Chen","year":"2023","journal-title":"Chinese Journal of Computers"},{"issue":"5","key":"10.1016\/j.neunet.2026.108896_bib0009","first-page":"685","article-title":"Reinforcement learning and its application to the game of go","volume":"42","author":"Chen","year":"2016","journal-title":"Acta Automatica Sinica"},{"key":"10.1016\/j.neunet.2026.108896_bib0010","series-title":"The twelfth international conference on learning representations","article-title":"Safe RLHF: Safe reinforcement learning from human feedback","author":"Dai","year":"2024"},{"issue":"4","key":"10.1016\/j.neunet.2026.108896_bib0011","doi-asserted-by":"crossref","first-page":"560","DOI":"10.1287\/mnsc.45.4.560","article-title":"Solving semi-Markov decision problems using average reward reinforcement learning","volume":"45","author":"Das","year":"1999","journal-title":"Management Science"},{"key":"10.1016\/j.neunet.2026.108896_bib0012","series-title":"Proceedings of the 11th international conference autonomous agents and multiagent systems","doi-asserted-by":"crossref","first-page":"433","DOI":"10.65109\/JJTT8551","article-title":"Dynamic potential-based reward shaping","author":"Devlin","year":"2012"},{"key":"10.1016\/j.neunet.2026.108896_bib0013","unstructured":"Guo, D., Yang, D., Zhang, H., Song, J., Zhang, R., Xu, R., Zhu, Q., Ma, S., Wang, P., Bi, X. et al. (2025). DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv: 2501.12948."},{"issue":"5","key":"10.1016\/j.neunet.2026.108896_bib0014","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/0893-6080(89)90018-X","article-title":"Convergent activation dynamics in continuous time networks","volume":"2","author":"Hirsch","year":"1989","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108896_bib0015","series-title":"Reinforcement learning for continuing problems using average reward","author":"Naik","year":"2024"},{"key":"10.1016\/j.neunet.2026.108896_bib0016","series-title":"Reward centering","first-page":"1995","volume":"4","author":"Naik","year":"2024"},{"key":"10.1016\/j.neunet.2026.108896_bib0017","series-title":"Proceedings of the 16th international conference machine learning","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"Ng","year":"1999"},{"key":"10.1016\/j.neunet.2026.108896_bib0018","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108896_bib0019","unstructured":"Patterson, D., Gonzalez, J., Le, Q., Liang, C., Munguia, L.-M., Rothchild, D, So, D., Texier, So, D., Texier, M., & Dean, J. (2021). Carbon emissions and large neural network training. arXiv preprint arXiv: 2104.10350."},{"issue":"31","key":"10.1016\/j.neunet.2026.108896_bib0020","doi-asserted-by":"crossref","first-page":"25663","DOI":"10.1007\/s00521-024-10620-5","article-title":"Average reward adjusted discounted reinforcement learning","volume":"37","author":"Schneckenreither","year":"2025","journal-title":"Neural Computing and Applications"},{"key":"10.1016\/j.neunet.2026.108896_bib0021","series-title":"Proceedings of the tenth international conference on machine learning","first-page":"298","article-title":"A reinforcement learning method for maximizing undiscounted rewards","volume":"vol. 298","author":"Schwartz","year":"1993"},{"issue":"7587","key":"10.1016\/j.neunet.2026.108896_bib0022","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"Nature"},{"key":"10.1016\/j.neunet.2026.108896_bib0023","first-page":"37719","article-title":"Exploit reward shifting in value-based deep-Rl: Optimistic curiosity-based exploration and conservative exploitation via linear reward shaping","volume":"35","author":"Sun","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108896_bib0024","series-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"10.1016\/j.neunet.2026.108896_bib0025","series-title":"Proceedings of the 26th international conference machine learning","first-page":"993","article-title":"Fast gradient-descent methods for temporal-difference learning with linear function approximation","author":"Sutton","year":"2009"},{"key":"10.1016\/j.neunet.2026.108896_bib0026","series-title":"Advances in neural information processing systems","first-page":"1609","article-title":"A convergent o(n) temporal-difference algorithm for off-policy learning with linear function approximation","author":"Sutton","year":"2008"},{"issue":"1","key":"10.1016\/j.neunet.2026.108896_bib0027","first-page":"2603","article-title":"An emphatic approach to the problem of off-policy temporal-difference learning","volume":"17","author":"Sutton","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.108896_bib0028","series-title":"International conference on machine learning","first-page":"10653","article-title":"Learning and planning in average-reward markov decision processes","author":"Wan","year":"2021"},{"key":"10.1016\/j.neunet.2026.108896_bib0029","series-title":"Proceedings of the thirtieth AAAI conference on artificial intelligence","first-page":"2258","article-title":"Efficient average reward reinforcement learning using constant shifting values","author":"Yang","year":"2016"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026003576?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026003576?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T03:14:07Z","timestamp":1781147647000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026003576"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":29,"alternative-id":["S0893608026003576"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108896","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Bellman error centering","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108896","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":"108896"}}