{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:44:24Z","timestamp":1770846264669,"version":"3.50.1"},"reference-count":14,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11343590","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"5546-5551","source":"Crossref","is-referenced-by-count":0,"title":["Balancing Exploration and Exploitation in Maximum Diffusion Reinforcement Learning Using Evolutionary Computation Algorithm"],"prefix":"10.1109","author":[{"given":"Ying","family":"Zhao","sequence":"first","affiliation":[{"name":"University of Aizu,Graduate School of Computer Science and Engineering,Aizuwakamatsu,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Pei","sequence":"additional","affiliation":[{"name":"University of Aizu,Computer Science Division,Aizuwakamatsu,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1196","article-title":"Evolution-guided policy gradient in reinforcement learning","author":"Khadka","year":"2018","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5728"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3493198"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref5","first-page":"1","article-title":"Prioritized experience replay","volume-title":"International Conference on Learning Representations (ICLR)","author":"Tom"},{"key":"ref6","first-page":"5048","article-title":"Hindsight experience replay","author":"Andrychowicz","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref7","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"AAAI Conference on Artificial Intelligence (AAAI)","author":"Henderson"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.011"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00829-3"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.106.620"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref14","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning (ICML)","author":"Haarnoja"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11343590.pdf?arnumber=11343590","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:53:00Z","timestamp":1770843180000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11343590\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11343590","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}