{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:22:08Z","timestamp":1766067728850,"version":"3.37.3"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&amp;D Program of China","award":["2022YFB4701400\/4701402"],"award-info":[{"award-number":["2022YFB4701400\/4701402"]}]},{"name":"bySZSTC","award":["JCYJ20190809172201639","WDZC20200820200655001"],"award-info":[{"award-number":["JCYJ20190809172201639","WDZC20200820200655001"]}]},{"name":"Shenzhen Key Laboratory","award":["ZDSYS20210623092001004"],"award-info":[{"award-number":["ZDSYS20210623092001004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/tg.2023.3259724","type":"journal-article","created":{"date-parts":[[2023,3,20]],"date-time":"2023-03-20T18:08:08Z","timestamp":1679335688000},"page":"225-234","source":"Crossref","is-referenced-by-count":6,"title":["The Fittest Wins: A Multistage Framework Achieving New SOTA in <i>ViZDoom<\/i> Competition"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0252-8250","authenticated-orcid":false,"given":"Shuxing","family":"Li","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0016-2056","authenticated-orcid":false,"given":"Jiawei","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}]},{"given":"Honghua","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Toronto, Toronto, ON, Canada"}]},{"given":"Yu","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3590-6676","authenticated-orcid":false,"given":"Chun","family":"Yuan","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8187-9736","authenticated-orcid":false,"given":"Peng","family":"Sun","sequence":"additional","affiliation":[{"name":"Tencent Robotics X, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1404-2415","authenticated-orcid":false,"given":"Lei","family":"Han","sequence":"additional","affiliation":[{"name":"Tencent Robotics X, Shenzhen, China"}]}],"member":"263","reference":[{"article-title":"OpenAI gym","year":"2016","author":"Brockman","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2019.2896986"},{"key":"ref5","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2834566"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref13","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":"ref14","first-page":"5048","article-title":"Hindsight experience replay","author":"Andrychowicz","year":"2017","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/459"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref17","article-title":"Emergent tool use from multi-agent autocurricula","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baker","year":"2020"},{"key":"ref18","first-page":"1025","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Gupta","year":"2020"},{"key":"ref19","article-title":"Clyde: A deep reinforcement learning DOOM playing agent","volume-title":"Proc. Workshops 31st AAAI Conf. Artif. Intell.","author":"Ratcliffe","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref21","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref22","article-title":"Training agent for first-person shooter game with actor-critic curriculum learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-16670-0_11"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/482"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3468857"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50012-5"},{"key":"ref27","article-title":"Policy distillation","volume-title":"Proc. 4th Int. Conf. Learn. Representations","author":"Rusu","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2877047"},{"issue":"11","key":"ref29","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/10474491\/10077442.pdf?arnumber=10077442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T07:29:23Z","timestamp":1725607763000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10077442\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":29,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tg.2023.3259724","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"type":"print","value":"2475-1502"},{"type":"electronic","value":"2475-1510"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}