{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T20:58:38Z","timestamp":1775681918797,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["21625348"],"award-info":[{"award-number":["21625348"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["21625110"],"award-info":[{"award-number":["21625110"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62506191"],"award-info":[{"award-number":["62506191"]}],"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":["62476128"],"award-info":[{"award-number":["62476128"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tnnls.2025.3626536","type":"journal-article","created":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:40:49Z","timestamp":1762368049000},"page":"1904-1918","source":"Crossref","is-referenced-by-count":0,"title":["ORAL: Adaptive Gap Increasing for Advantage Learning via Occam\u2019s Razor Principle"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7960-5533","authenticated-orcid":false,"given":"Zhe","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4398-1418","authenticated-orcid":false,"given":"Yongle","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuyang","family":"Long","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6079-2818","authenticated-orcid":false,"given":"Jia","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juanjuan","family":"Weng","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7804-0286","authenticated-orcid":false,"given":"Zhetao","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaozhong","family":"Gan","sequence":"additional","affiliation":[{"name":"Qiyuan Lab, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2683-8667","authenticated-orcid":false,"given":"Xiaoyang","family":"Tan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3296765"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3209154"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3477600"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-023-06481-z"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3183865"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3089493"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3278715"},{"key":"ref10","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref11","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10303"},{"key":"ref13","article-title":"Unifying value iteration, advantage learning, and dynamic policy programming","author":"Kozuno","year":"2017","journal-title":"arXiv:1710.10866"},{"key":"ref14","first-page":"172","article-title":"Action-gap phenomenon in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Farahmand"},{"issue":"1","key":"ref15","first-page":"3207","article-title":"Dynamic policy programming","volume":"13","author":"Azar","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","first-page":"4235","article-title":"Munchausen reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vieillard"},{"key":"ref17","first-page":"12163","article-title":"Leverage the average: An analysis of KL regularization in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vieillard"},{"key":"ref18","article-title":"Gap-increasing policy evaluation for efficient and noise-tolerant reinforcement learning","author":"Kozuno","year":"2019","journal-title":"arXiv:1906.07586"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20620"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.65109\/kkvm3697"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20900"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref24","first-page":"2411","article-title":"Speedy Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Ghavamzadeh"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1110.0532"},{"key":"ref26","article-title":"Reinforcement learning through gradient descent","author":"Baird","year":"1999"},{"key":"ref27","first-page":"14134","article-title":"Using a logarithmic mapping to enable lower discount factors in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Seijen"},{"key":"ref28","first-page":"6540","article-title":"On the convergence of smooth regularized approximate value iteration schemes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Smirnova"},{"key":"ref29","first-page":"3878","article-title":"Self-imitation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Oh"},{"key":"ref30","first-page":"1054","article-title":"Safe and efficient off-policy reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Munos"},{"key":"ref31","first-page":"47815","article-title":"Action gaps and advantages in continuous-time distributional reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Wiltzer"},{"key":"ref32","first-page":"1","article-title":"Offline reinforcement learning with munchausen regularization","volume-title":"Proc. Offline Reinforcement Learn. Workshop Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref33","article-title":"Scalable offline reinforcement learning for mean field games","author":"Brunnbauer","year":"2024","journal-title":"arXiv:2410.17898"},{"key":"ref34","first-page":"2995","article-title":"Theoretical analysis of efficiency and robustness of softmax and gap-increasing operators in reinforcement learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"Kozuno"},{"key":"ref35","article-title":"Reinforcement learning: Theory and algorithms","author":"Agarwal","year":"2019"},{"key":"ref36","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gu"},{"key":"ref37","article-title":"MinAtar: An Atari-inspired testbed for thorough and reproducible reinforcement learning experiments","author":"Young","year":"2019","journal-title":"arXiv:1903.03176"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref39","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref40","article-title":"Maxmin Q-learning: Controlling the estimation bias of Q-learning","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"Lan"},{"key":"ref41","first-page":"1","article-title":"Memory-efficient reinforcement learning with value-based knowledge consolidation","volume":"2022","author":"Lan","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i20.35393"},{"key":"ref43","first-page":"27875","article-title":"Value-evolutionary-based reinforcement learning","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1561\/2400000026"},{"key":"ref45","first-page":"511","article-title":"Robust reinforcement learning using least squares policy iteration with provable performance guarantees","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Badrinath"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11475606\/11227018.pdf?arnumber=11227018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T20:06:53Z","timestamp":1775678813000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227018\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":45,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3626536","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}