{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T16:56:09Z","timestamp":1762102569315,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"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":[[2020,8]]},"DOI":"10.1109\/cog47356.2020.9231589","type":"proceedings-article","created":{"date-parts":[[2020,10,21]],"date-time":"2020-10-21T18:05:50Z","timestamp":1603303550000},"page":"245-252","source":"Crossref","is-referenced-by-count":4,"title":["Manipulating the Distributions of Experience used for Self-Play Learning in Expert Iteration"],"prefix":"10.1109","author":[{"given":"Dennis J. N. J.","family":"Soemers","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Piette","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew","family":"Stephenson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cameron","family":"Browne","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1023\/B:AIRE.0000036264.95672.64"},{"article-title":"OpenSpiel: A framework for reinforcement learning in games","year":"2019","author":"lanctot","key":"ref32"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-019-45619-9","article-title":"?-rank: Multi-agent evaluation by evolution","volume":"9","author":"omidshafiei","year":"2019","journal-title":"Scientific Reports"},{"key":"ref30","first-page":"754","author":"cazenave","year":"2015","journal-title":"Proc Intern Joint Conf Artificial Intel (IJCAI)"},{"article-title":"Accelerating self-play learning in Go","year":"2019","author":"wu","key":"ref10"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1126\/science.aau6249","article-title":"Human-level performance in 3D multiplayer games with population-based reinforcement learning","volume":"364","author":"jaderberg","year":"2019","journal-title":"Science"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848006"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref13"},{"journal-title":"The Role of Exploration in Learning Control","year":"1992","author":"thrun","key":"ref14"},{"key":"ref15","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1.5.263"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref18","first-page":"759","article-title":"Eligibility traces for off-policy policy evaluation","author":"precup","year":"2000","journal-title":"Proc 17th Int Conf Mach Learn (ICML)"},{"key":"ref19","first-page":"417","article-title":"Off-policy temporal-difference learning with function approximation","author":"precup","year":"2001","journal-title":"Proc 18th Int Conf Mach Learn (ICML)"},{"article-title":"Generating sequences with recurrent neural networks","year":"2013","author":"graves","key":"ref28"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in StarCraft II using multi-agent reinforcement learning","volume":"575","author":"vinyals","year":"2019","journal-title":"Nature"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2019.8790141"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-75538-8_7"},{"article-title":"Dopamine: A research framework for deep reinforcement learning","year":"2018","author":"castro","key":"ref29"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1007\/11871842_29","article-title":"Bandit based Monte-Carlo planning","volume":"4212","author":"kocsis","year":"2006","journal-title":"Machine Learning ECML 2006 ser LNCS"},{"key":"ref8","first-page":"6244","article-title":"ELF OpenGo: An analysis and open reimplementation of AlphaZero","author":"tian","year":"2019","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref2","first-page":"5360","article-title":"Thinking fast and slow with deep learning and tree search","volume":"30","author":"anthony","year":"2017","journal-title":"Adv in Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852266"},{"key":"ref1","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":"ref20","article-title":"Weighted importance sampling for off-policy learning with linear function approximation","volume":"27","author":"mahmood","year":"2014","journal-title":"Adv in Neural Inf Process Syst"},{"key":"ref22","first-page":"3215","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2018","journal-title":"Proc AAAI Conf Artif Intell (AAAI) AAAI"},{"key":"ref21","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref23","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":"ref26","first-page":"70","article-title":"Strategic features for general games","author":"browne","year":"2019","journal-title":"Proc 2nd Workshop on Knowledge Extraction from Games (KEG)"},{"key":"ref25","article-title":"Ludii - the ludemic general game system","author":"piette","year":"2020","journal-title":"Proc 2020 Eur Conf Artif Intell"}],"event":{"name":"2020 IEEE Conference on Games (CoG)","start":{"date-parts":[[2020,8,24]]},"location":"Osaka, Japan","end":{"date-parts":[[2020,8,27]]}},"container-title":["2020 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9222389\/9231525\/09231589.pdf?arnumber=9231589","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T15:58:00Z","timestamp":1656345480000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9231589\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/cog47356.2020.9231589","relation":{},"subject":[],"published":{"date-parts":[[2020,8]]}}}