{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T07:16:38Z","timestamp":1769325398179,"version":"3.49.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/Crown.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,8]]},"DOI":"10.1109\/cig.2019.8848006","type":"proceedings-article","created":{"date-parts":[[2019,9,26]],"date-time":"2019-09-26T21:49:14Z","timestamp":1569534554000},"page":"1-8","source":"Crossref","is-referenced-by-count":22,"title":["A Generalized Framework for Self-Play Training"],"prefix":"10.1109","author":[{"given":"Daniel","family":"Hernandez","sequence":"first","affiliation":[]},{"given":"Kevin","family":"Denamganai","sequence":"additional","affiliation":[]},{"given":"Yuan","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Peter","family":"York","sequence":"additional","affiliation":[]},{"given":"Sam","family":"Devlin","sequence":"additional","affiliation":[]},{"given":"Spyridon","family":"Samothrakis","sequence":"additional","affiliation":[]},{"given":"James Alfred","family":"Walker","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"maaten","year":"2008"},{"key":"ref32","article-title":"Human-level performance in firstperson multiplayer games with population-based deep reinforcement learning","author":"jaderberg","year":"0"},{"key":"ref31","article-title":"Open-ended Learning in Symmetric Zero-sum Games","author":"balduzzi","year":"0"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref36","first-page":"1","article-title":"OpenAI Gym","author":"brockman","year":"2016"},{"key":"ref35","article-title":"Comparing UCT versus CFR in simultaneous games","author":"shafiei","year":"2009","journal-title":"Proc IJCAI Workshop General Game Playing"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1990.137821"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of Go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref12","first-page":"1","article-title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","author":"silver","year":"2017"},{"key":"ref13","first-page":"1","article-title":"Thinking Fast and Slow with Deep Learning and Tree Search","author":"anthony","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6614996"},{"key":"ref15","article-title":"Beating the World’s Best at Super Smash Bros. with Deep Reinforcement Learning","author":"firoiu","year":"2017"},{"key":"ref16","first-page":"1","article-title":"Playing Atari with Deep Reinforcement Learning","author":"mnih","year":"2013"},{"key":"ref17","first-page":"1","article-title":"Emergent Complexity via Multi-Agent Competition","volume":"2","author":"bansal","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3233\/KES-2010-0206"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.7142\/igakutoshokan.48.95"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-44973-4_19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref27","first-page":"1","article-title":"Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents","author":"leibo","year":"2018"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1007\/BF00992697","article-title":"Practical Issues in Temporal Difference Learning","volume":"8","author":"tesauro","year":"1992","journal-title":"Machine Learning"},{"key":"ref6","article-title":"Learning to Run with Reward Shaping from Video Data","author":"malysheva","year":"2018"},{"key":"ref29","first-page":"1","article-title":"Prioritized Experience Replay","author":"schaul","year":"2015"},{"key":"ref5","article-title":"Playing hard exploration games by watching YouTube","author":"aytar","year":"2018"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1147\/rd.33.0210","article-title":"Some studies in machine learning using the game of checkers","volume":"3","author":"samuel","year":"1959","journal-title":"IBM Journal"},{"key":"ref7","first-page":"10","article-title":"Domain-independent optimistic initialization for reinforcement learning","author":"machado","year":"2014"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of {Go} with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","first-page":"1","article-title":"Sutton-roleof-tracking","author":"sutton","year":"2007"},{"key":"ref22","first-page":"1","article-title":"RL$ˆ2$: Fast Reinforcement Learning via Slow Reinforcement Learning","author":"duan","year":"2016"},{"key":"ref21","first-page":"1633","article-title":"Transfer Learning for Reinforcement Learning Domain.pdf","volume":"10","author":"taylor","year":"2009"},{"key":"ref24","article-title":"A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning","author":"lanctot","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jet.2005.12.010"},{"key":"ref26","first-page":"1","article-title":"DeepMind Lab","author":"beattie","year":"2016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/0042-6989(95)00016-X"}],"event":{"name":"2019 IEEE Conference on Games (CoG)","location":"London, United Kingdom","start":{"date-parts":[[2019,8,20]]},"end":{"date-parts":[[2019,8,23]]}},"container-title":["2019 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8844551\/8847948\/08848006.pdf?arnumber=8848006","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T10:50:49Z","timestamp":1658141449000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8848006\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/cig.2019.8848006","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}