{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:41:32Z","timestamp":1781797292890,"version":"3.54.5"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"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","award":["61876181"],"award-info":[{"award-number":["61876181"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61721004"],"award-info":[{"award-number":["61721004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Nova Program of Science and Technology","award":["Z191100001119043"],"award-info":[{"award-number":["Z191100001119043"]}]},{"DOI":"10.13039\/501100012492","name":"Youth Innovation Promotion Association","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012492","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1109\/tg.2021.3134259","type":"journal-article","created":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T21:04:21Z","timestamp":1639429461000},"page":"644-653","source":"Crossref","is-referenced-by-count":10,"title":["Deep Reinforcement Learning With Part-Aware Exploration Bonus in Video Games"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1766-5634","authenticated-orcid":false,"given":"Pei","family":"Xu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3442-6275","authenticated-orcid":false,"given":"Qiyue","family":"Yin","sequence":"additional","affiliation":[{"name":"Center for Research on Intelligent System and Engineering, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9970-394X","authenticated-orcid":false,"given":"Junge","family":"Zhang","sequence":"additional","affiliation":[{"name":"Center for Research on Intelligent System and Engineering, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2677-9273","authenticated-orcid":false,"given":"Kaiqi","family":"Huang","sequence":"additional","affiliation":[{"name":"Center for Research on Intelligent System and Engineering and the National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"On bonus based exploration methods in the arcade learning environment","author":"taiga","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref32","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref31","first-page":"424","article-title":"3D object proposals for accurate object class detection","author":"chen","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299170"},{"key":"ref35","article-title":"Never give up: Learning directed exploration strategies","author":"badia","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref34","first-page":"507","article-title":"Agent57: Outperforming the Atari human benchmark","author":"badia","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","article-title":"Incentivizing exploration in reinforcement learning with deep predictive models","volume":"abs 1507 814","author":"stadie","year":"2015","journal-title":"CoRR"},{"key":"ref11","article-title":"Learning to perform physics experiments via deep reinforcement learning","author":"denil","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref12","first-page":"4026","article-title":"Deep exploration via bootstrapped DQN","author":"osband","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref13","article-title":"Noisy networks for exploration","author":"fortunato","year":"0","journal-title":"Proc Int Conf Learn Representation"},{"key":"ref14","article-title":"Parameter space noise for exploration","author":"plappert","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref15","article-title":"Intrinsic motivation and automatic curricula via asymmetric self-play","author":"sukhbaatar","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref16","article-title":"Variational intrinsic control","author":"gregor","year":"0","journal-title":"Proc Int Conf Learn Representations Workshops"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2891792"},{"key":"ref18","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref19","article-title":"Deep attention recurrent Q-network","volume":"abs 1512 1693","author":"sorokin","year":"2015","journal-title":"CoRR"},{"key":"ref28","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","article-title":"Large-scale study of curiosity-driven learning","author":"burda","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref27","article-title":"OpenAI Gym","volume":"abs 1606 1540","author":"brockman","year":"2016","journal-title":"CoRR"},{"key":"ref3","first-page":"5062","article-title":"Self-supervised exploration via disagreement","author":"pathak","year":"0","journal-title":"Proc IEEE Int Conf Mach Learn"},{"key":"ref6","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.211"},{"key":"ref5","article-title":"Exploration by random network distillation","author":"burda","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref8","first-page":"2577","article-title":"EX2: Exploration with exemplar models for deep reinforcement learning","author":"fu","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref7","first-page":"2721","article-title":"Count-based exploration with neural density models","author":"ostrovski","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref9","first-page":"222","article-title":"A possibility for implementing curiosity and boredom in model-building neural controllers","author":"schmidhuber","year":"0","journal-title":"Proc Int Conf Simul Adapt Behav"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_41"},{"key":"ref22","first-page":"12350","article-title":"Towards interpretable reinforcement learning using attention augmented agents","author":"mott","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref21","article-title":"Deep reinforcement learning with relational inductive biases","author":"zambaldi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref24","article-title":"Contingency-aware exploration in reinforcement learning","author":"choi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3377930.3389847"},{"key":"ref26","article-title":"Proximal policy optimization algorithms","volume":"abs 1707 6347","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref25","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"0","journal-title":"Proc Int Conf Neural Inf Process"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/9987665\/09647912.pdf?arnumber=9647912","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T19:12:01Z","timestamp":1673896321000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9647912\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":35,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tg.2021.3134259","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]}}}