{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T07:14:10Z","timestamp":1761808450164,"version":"3.37.3"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/Crown.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"EPSRC Centre for Doctoral Training in Intelligent Games and Game Intelligence","award":["EP\/L015846\/1"],"award-info":[{"award-number":["EP\/L015846\/1"]}]},{"name":"Digital Creativity Labs"},{"name":"EPSRC\/AHRC\/Innovate U.K.","award":["EP\/M023265\/1"],"award-info":[{"award-number":["EP\/M023265\/1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/tg.2021.3058898","type":"journal-article","created":{"date-parts":[[2021,2,11]],"date-time":"2021-02-11T22:06:45Z","timestamp":1613081205000},"page":"221-231","source":"Crossref","is-referenced-by-count":10,"title":["A Comparison of Self-Play Algorithms Under a Generalized Framework"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1667-2579","authenticated-orcid":false,"given":"Daniel","family":"Hernandez","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of York, York, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8776-4331","authenticated-orcid":false,"given":"Kevin","family":"Denamganai","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of York, York, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7769-3090","authenticated-orcid":false,"given":"Sam","family":"Devlin","sequence":"additional","affiliation":[{"name":"Microsoft Research, Cambridge, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1902-9690","authenticated-orcid":false,"given":"Spyridon","family":"Samothrakis","sequence":"additional","affiliation":[{"name":"Institute of Analytics & Data Science, University of Essex, Colchester, U.K."}]},{"given":"James Alfred","family":"Walker","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of York, York, U.K."}]}],"member":"263","reference":[{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6223"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6614996"},{"key":"ref4","first-page":"4190","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lanctot","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1147\/rd.33.0210"},{"key":"ref6","article-title":"Open-ended learning in symmetric zero-sum games","volume-title":"CORR","volume":"abs\/1901.08106","author":"Balduzzi","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-45619-9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1990.137821"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref12","first-page":"5360","article-title":"Thinking fast and slow with deep learning and tree search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Anthony","year":"2017"},{"key":"ref13","article-title":"Emergent complexity via multi-agent competition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bansal","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3233\/KES-2010-0206"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273606"},{"issue":"7","key":"ref16","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"Taylor","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref17","article-title":"Rl$^2$: Fast reinforcement learning via slow reinforcement learning","volume-title":"CoRR","volume":"abs\/1611.02779","author":"Duan","year":"2016"},{"key":"ref18","article-title":"Dota 2 with large scale deep reinforcement learning","volume-title":"CoRR","volume":"abs\/1912.06680","author":"Berner","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref21","article-title":"A generalized training approach for multiagent learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Muller","year":"2019"},{"key":"ref22","article-title":"Real world games look like spinning tops","volume-title":"CoRR","volume":"abs\/2004.09468","author":"Czarnecki","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-44973-4_19"},{"key":"ref24","article-title":"Prioritized experience replay","volume-title":"Proc. 4th Int. Conf. Learn. Representations","author":"Schaul","year":"2016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/bf00992696"},{"key":"ref26","first-page":"3268","article-title":"Re-evaluating evaluation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Balduzzi","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-011-0841-3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848006"},{"key":"ref29","first-page":"12 270","article-title":"Multiagent evaluation under incomplete information","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rowland","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/9797039\/09353226.pdf?arnumber=9353226","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:57:13Z","timestamp":1704844633000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9353226\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":30,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tg.2021.3058898","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"type":"print","value":"2475-1502"},{"type":"electronic","value":"2475-1510"}],"subject":[],"published":{"date-parts":[[2022,6]]}}}