{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T05:51:27Z","timestamp":1781761887696,"version":"3.54.5"},"reference-count":25,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100007620","name":"Department of Education of Liaoning Province","doi-asserted-by":"publisher","award":["LJKMZ20220754"],"award-info":[{"award-number":["LJKMZ20220754"]}],"id":[{"id":"10.13039\/501100007620","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007620","name":"Department of Education of Liaoning Province","doi-asserted-by":"publisher","award":["LJKMZ20220723"],"award-info":[{"award-number":["LJKMZ20220723"]}],"id":[{"id":"10.13039\/501100007620","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tg.2026.3683937","type":"journal-article","created":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T19:55:22Z","timestamp":1776369322000},"page":"340-348","source":"Crossref","is-referenced-by-count":0,"title":["Enhanced Policy Update Mechanism for PPO-Inspired Algorithms in Intelligent Agent-Based Games"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8573-4876","authenticated-orcid":false,"given":"Xuyan","family":"Jin","sequence":"first","affiliation":[{"name":"Liaoning Petrochemical University, FUSHUN, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4822-3433","authenticated-orcid":false,"given":"Yang","family":"Cao","sequence":"additional","affiliation":[{"name":"Liaoning Petrochemical University, FUSHUN, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7210-5581","authenticated-orcid":false,"given":"Hongfei","family":"Yu","sequence":"additional","affiliation":[{"name":"Liaoning Petrochemical University, FUSHUN, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4392-4274","authenticated-orcid":false,"given":"Hang","family":"Deng","sequence":"additional","affiliation":[{"name":"Liaoning Petrochemical University, FUSHUN, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuejian","family":"Chen","sequence":"additional","affiliation":[{"name":"Liaoning Petrochemical University, FUSHUN, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1953"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s13235-012-0059-2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref4","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref7","first-page":"3215","article-title":"Rainbow: Combining improvements in deep reinforcement learning","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Hessel","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref9","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. 13th Int. Conf. Neural Inf. Process. Syst.","author":"Sutton","year":"1999"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017746"},{"issue":"1011","key":"ref11","first-page":"1655","article-title":"Revisiting natural gradient for deep networks","volume":"37","author":"Pascanu","year":"2014","journal-title":"Comput. Sci."},{"key":"ref12","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref13","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"},{"key":"ref14","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref15","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019"},{"key":"ref16","article-title":"DI-Engine: A universal AI system\/engine for decision intelligence","author":"Niu","year":"2021"},{"key":"ref17","article-title":"Emergent tool use from multi-agent autocurricula","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baker","year":"2019"},{"key":"ref18","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Yu","year":"2022"},{"key":"ref19","article-title":"Adversarial attacks on neural network policies","author":"Huang","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/591"},{"key":"ref21","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"Salimans","year":"2017"},{"key":"ref22","first-page":"970","article-title":"Structured evolution with compact architectures for scalable policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Choromanski","year":"2018"},{"key":"ref23","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref24","article-title":"Diversity is all you need: Learning skills without a reward function","author":"Eysenbach","year":"2018"},{"key":"ref25","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Laskin","year":"2020"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7782673\/11569647\/11482497.pdf?arnumber=11482497","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T04:55:53Z","timestamp":1781758553000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11482497\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":25,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tg.2026.3683937","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}