{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:16:26Z","timestamp":1774419386439,"version":"3.50.1"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889888","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Regret Optimization Experience Replay in Off-Policy Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Jie","family":"Zhang","sequence":"first","affiliation":[{"name":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yirong","family":"Yao","sequence":"additional","affiliation":[{"name":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"He","sequence":"additional","affiliation":[{"name":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiqun","family":"Niu","sequence":"additional","affiliation":[{"name":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chongjun","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University,State Key Laboratory for Novel Software Technology,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":"10.1109\/CVPR42600.2020.01117"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref5","first-page":"4851","article-title":"Remember and forget for experience replay","volume-title":"International Conference on Machine Learning","author":"Novati"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/463"},{"key":"ref7","article-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116023"},{"key":"ref9","article-title":"Curriculum-guided hindsight experience replay","volume":"32","author":"Fang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref10","first-page":"1198","article-title":"Proving theorems using incremental learning and hindsight experience replay","volume-title":"International Conference on Machine Learning","author":"Ayg\u00fcn"},{"key":"ref11","first-page":"8545","article-title":"Off-policy actorcritic with shared experience replay","volume-title":"International Conference on Machine Learning","author":"Schmitt"},{"key":"ref12","first-page":"17604","article-title":"Regret minimization experience replay in off-policy reinforcement learning","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","article-title":"Stratified experience replay: Correcting multiplicity bias in off-policy reinforcement learning","author":"Daley","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6049"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref16","article-title":"Openai gym","author":"Brockman","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889888.pdf?arnumber=10889888","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:36Z","timestamp":1774416156000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889888\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889888","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}