{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T10:51:59Z","timestamp":1768819919882,"version":"3.49.0"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100013099","name":"Basic Scientific Research Fund of Liaoning Provincial Education Department","doi-asserted-by":"publisher","award":["LJKMZ20220754"],"award-info":[{"award-number":["LJKMZ20220754"]}],"id":[{"id":"10.13039\/501100013099","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013099","name":"Basic Scientific Research Fund of Liaoning Provincial Education Department","doi-asserted-by":"publisher","award":["LJKMZ20220723"],"award-info":[{"award-number":["LJKMZ20220723"]}],"id":[{"id":"10.13039\/501100013099","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3450297","type":"journal-article","created":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T17:33:40Z","timestamp":1724693620000},"page":"120827-120839","source":"Crossref","is-referenced-by-count":1,"title":["M0RV Model: Advancing the MuZero Algorithm Through Strategic Data Optimization Reuse and Value Function Refinement"],"prefix":"10.1109","volume":"12","author":[{"given":"Xuejian","family":"Chen","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Software, Liaoning Petrochemical University, Fushun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6357-7118","authenticated-orcid":false,"given":"Yang","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Software, Liaoning Petrochemical University, Fushun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7210-5581","authenticated-orcid":false,"given":"Hongfei","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Software, Liaoning Petrochemical University, Fushun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Caihua","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Software, Liaoning Petrochemical University, Fushun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2379-3_11"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(01)00129-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref4","first-page":"3191","article-title":"The predictron: End-to-end learning and planning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00444-8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref9","first-page":"1","article-title":"Sample-efficient deep reinforcement learning via episodic backward update","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lee"},{"key":"ref10","first-page":"25476","article-title":"Mastering Atari games with limited data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ye"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604698"},{"key":"ref12","first-page":"4476","article-title":"Learning and planning in complex action spaces","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hubert"},{"key":"ref13","article-title":"Policy regularization via noisy advantage values for cooperative multi-agent actor-critic methods","author":"Hu","year":"2021","journal-title":"Int. Found. Auton. Agents Multiagent Syst."},{"key":"ref14","volume-title":"Alphazero to alpha hero: A pre-study on additional tree sampling within self-play reinforcement learning","author":"Carlsson","year":"2019"},{"key":"ref15","article-title":"A0C: Alpha zero in continuous action space","author":"Moerland","year":"2018","journal-title":"arXiv:1805.09613"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-05928-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2019.2901021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2019.2896986"},{"key":"ref19","article-title":"Model-based reinforcement learning for Atari","author":"Kaiser","year":"2019","journal-title":"arXiv:1903.00374"},{"key":"ref20","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref21","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_29"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-27992-3_6"},{"key":"ref24","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":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-75538-8_7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40988-2_13"},{"key":"ref27","first-page":"3061","article-title":"Revisiting fundamentals of experience replay","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fedus"},{"key":"ref28","first-page":"14753","article-title":"Feature selection using e-values","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Majumdar"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.2023.2183262"},{"key":"ref30","article-title":"Group validation in recommender systems: Framework for multi-layer performance evaluation","author":"Al Jurdi","year":"2022","journal-title":"arXiv:2207.09320"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10648685.pdf?arnumber=10648685","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T05:55:36Z","timestamp":1726034136000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10648685\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3450297","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}