{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T16:55:12Z","timestamp":1770915312547,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"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":[[2020,12,1]]},"DOI":"10.1109\/ssci47803.2020.9308290","type":"proceedings-article","created":{"date-parts":[[2021,1,5]],"date-time":"2021-01-05T23:12:38Z","timestamp":1609888358000},"page":"2600-2607","source":"Crossref","is-referenced-by-count":3,"title":["Coevolutionary Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"David","family":"Cotton","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason","family":"Traish","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zenon","family":"Chaczko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","author":"elo","year":"1978","journal-title":"The Rating of Chessplayers Past and Present"},{"key":"ref32","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"arXiv preprint arXiv 1802 09085"},{"key":"ref31","article-title":"Collaborative evolutionary reinforcement learning","author":"khadka","year":"2019","journal-title":"arXiv preprint arXiv 1905 00571"},{"key":"ref30","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017","journal-title":"arXiv preprint arXiv 1703 09042"},{"key":"ref35","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref34","first-page":"72","article-title":"Efficient selectivity and backup operators in monte-carlo tree search","author":"coulom","year":"2006","journal-title":"International conference on computers and games"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(93)90058-4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref15","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2017","journal-title":"arXiv preprint arXiv 1710 02298"},{"key":"ref16","first-page":"5","article-title":"Deep reinforcement learning with double q-learning","volume":"2","author":"van hasselt","year":"0","journal-title":"AAAI"},{"key":"ref17","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015","journal-title":"arXiv preprint arXiv 1511 05271"},{"key":"ref18","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv preprint arXiv 1511 05952"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993045"},{"key":"ref4","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":"ref27","first-page":"762","article-title":"Training feedforward neural networks using genetic algorithms","volume":"89","author":"montana","year":"0","journal-title":"IJCAI"},{"key":"ref3","first-page":"267","author":"tesauro","year":"1994","journal-title":"Td-gammon A self-teaching backgammon program"},{"key":"ref6","first-page":"10","article-title":"Why did td-gammon work?","author":"pollack","year":"1997","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"key":"ref5","article-title":"Dota 2 with large scale deep reinforcement learning","author":"berner","year":"2019","journal-title":"arXiv preprint arXiv 1912 06680"},{"key":"ref8","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":"ref7","article-title":"Open-ended learning in symmetric zero-sum games","author":"balduzzi","year":"2019","journal-title":"arXiv preprint arXiv 1901 10055"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref9","article-title":"Emergent complexity via multi-agent competition","author":"bansal","year":"2017","journal-title":"arXiv preprint arXiv 1710 03748"},{"key":"ref1","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"2017","journal-title":"arXiv preprint arXiv 1707 06892"},{"key":"ref22","first-page":"2","author":"shannon","year":"1988","journal-title":"Programming A Computer for Playing Chess"},{"key":"ref21","article-title":"Noisy networks for exploration","author":"fortunato","year":"2017","journal-title":"arXiv preprint arXiv 1706 10295"},{"key":"ref24","article-title":"Population based training of neural networks","author":"jaderberg","year":"2017","journal-title":"arXiv preprint arXiv 1711 09846"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1147\/rd.116.0601","article-title":"Some studies in machine learning using the game of checkers. ii—recent progress","volume":"11","author":"samuel","year":"1967","journal-title":"IBM Journal of Research and Development"},{"key":"ref26","article-title":"An analysis of cooperative coevolutionary algorithms","author":"wiegand","year":"2003"},{"key":"ref25","article-title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","author":"jaderberg","year":"2018","journal-title":"arXiv preprint arXiv 1807 01281"}],"event":{"name":"2020 IEEE Symposium Series on Computational Intelligence (SSCI)","location":"Canberra, ACT, Australia","start":{"date-parts":[[2020,12,1]]},"end":{"date-parts":[[2020,12,4]]}},"container-title":["2020 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9308061\/9308107\/09308290.pdf?arnumber=9308290","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T15:16:27Z","timestamp":1656602187000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9308290\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,1]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/ssci47803.2020.9308290","relation":{},"subject":[],"published":{"date-parts":[[2020,12,1]]}}}