{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T23:14:16Z","timestamp":1740179656344,"version":"3.37.3"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1717324"],"award-info":[{"award-number":["1717324"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/tg.2022.3151025","type":"journal-article","created":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T02:34:05Z","timestamp":1644892445000},"page":"157-170","source":"Crossref","is-referenced-by-count":0,"title":["Transfer Dynamics in Emergent Evolutionary Curricula"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6261-242X","authenticated-orcid":false,"given":"Aaron","family":"Dharna","sequence":"first","affiliation":[{"name":"New Jersey Institute of Technology, Newark, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amy K.","family":"Hoover","sequence":"additional","affiliation":[{"name":"New Jersey Institute of Technology, Newark, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3128-4598","authenticated-orcid":false,"given":"Julian","family":"Togelius","sequence":"additional","affiliation":[{"name":"New York University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3259-3205","authenticated-orcid":false,"given":"Lisa B.","family":"Soros","sequence":"additional","affiliation":[{"name":"Cross Labs, Cross Compass Ltd., Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Loss is its own reward: Self-supervision for reinforcement learning","year":"2016","author":"shelhamer","key":"ref13"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3377930.3390221"},{"key":"ref12","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume":"70","author":"finn","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref56","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","author":"yu","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref15","first-page":"1","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"narvekar","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321876"},{"article-title":"Illuminating generalization in deep reinforcement learning through procedural level generation","year":"2018","author":"justesen","key":"ref53"},{"article-title":"StarCraft II: A new challenge for reinforcement learning","year":"2017","author":"vinyals","key":"ref52"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref55","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3377930.3390147"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231907"},{"key":"ref17","first-page":"1","article-title":"Transfer deep reinforcement learning in 3D environments: An empirical study","author":"chaplot","year":"2016","journal-title":"Proc 29th Int Conf Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref18","first-page":"1","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"nagabandi","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"article-title":"Starcraft II: A new challenge for reinforcement learning","year":"2017","author":"vinyals","key":"ref51"},{"key":"ref50","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"0","journal-title":"Proc 16th Int Conf Mach Learn"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37798-3_1"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/nature14422"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1017\/S0094837300004310"},{"journal-title":"Cluster Analysis for Researchers","year":"2004","author":"romesburg","key":"ref47"},{"key":"ref42","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":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2001576.2001606"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01155"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390225"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref9","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":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2015.2402393"},{"key":"ref3","first-page":"9940","article-title":"Enhanced POET: Open-ended reinforcement learning through unbounded invention of learning challenges and their solutions","volume":"119","author":"wang","year":"0","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2018.2857725"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_29"},{"article-title":"Action guidance: Getting the best of sparse rewards and shaped rewards for real-time strategy games","year":"2020","author":"huang","key":"ref40"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2014.2352795"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2019.2901021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008202821328"},{"article-title":"Evolution strategies as a scalable alternative to reinforcement learning","year":"2017","author":"salimans","key":"ref36"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1830483.1830503"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/artl_a_00286"},{"article-title":"Necessary conditions for open-ended evolution","year":"2018","author":"soros","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.7551\/978-0-262-32621-6-ch128"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v16i1.7431"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321799"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/EVCO_a_00025"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860443"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3319619.3321894"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/4235.942536"},{"article-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"berner","key":"ref25"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341571"},{"key":"ref22","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2823329"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860443"},{"key":"ref27","first-page":"987","author":"popovici","year":"2012","journal-title":"Coevolutionary Principles"},{"key":"ref29","first-page":"4193","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","volume":"30","author":"lanctot","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/10153940\/09712431.pdf?arnumber=9712431","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T18:34:08Z","timestamp":1688409248000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9712431\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":57,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tg.2022.3151025","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"type":"print","value":"2475-1502"},{"type":"electronic","value":"2475-1510"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}