{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:40:48Z","timestamp":1776886848131,"version":"3.51.2"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095379","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Complementary Learning System Based Intrinsic Reward in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Zijian","family":"Gao","sequence":"first","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kele","family":"Xu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongda","family":"Jia","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianjiao","family":"Wan","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Ding","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dawei","family":"Feng","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinjun","family":"Mao","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaimin","family":"Wang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ANNES.1993.323080"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.108.2.311"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref14","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume":"30","author":"tarvainen","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Efficient exploration via state marginal matching","author":"lee","year":"2019","journal-title":"arXiv preprint arXiv 1906 05190"},{"key":"ref11","article-title":"Never give up: Learning directed exploration strategies","author":"badia","year":"2020","journal-title":"arXiv preprint arXiv 2002 06755"},{"key":"ref22","first-page":"6736","article-title":"Aps: Active pretraining with successor features","author":"liu","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2012.6252962"},{"key":"ref21","article-title":"Diversity is all you need: Learning skills without a reward function","author":"eysenbach","year":"2018","journal-title":"arXiv preprint arXiv 1802 06360"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref17","article-title":"Urlb: Unsupervised reinforcement learning benchmark","author":"laskin","year":"2021","journal-title":"Deep RL Workshop NeurIPS 2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpa.2020.100022"},{"key":"ref19","first-page":"11920","article-title":"Reinforcement learning with prototypical representations","author":"yarats","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref18","article-title":"Behavior from the void: Unsupervised active pre-training","volume":"34","author":"liu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Learning fast, learning slow: A general continual learning method based on complementary learning system","author":"arani","year":"2022","journal-title":"arXiv preprint arXiv 2201 12604"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2016.05.004"},{"key":"ref4","article-title":"Exploration by random network distillation","author":"burda","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/1064546053278973"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref5","first-page":"5062","article-title":"Self-supervised exploration via disagreement","author":"pathak","year":"2019","journal-title":"International Conference on Machine Learning"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095379.pdf?arnumber=10095379","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T18:56:59Z","timestamp":1699901819000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095379\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095379","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}