{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T00:54:59Z","timestamp":1767833699713,"version":"3.49.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906081"],"award-info":[{"award-number":["61906081"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["RCBS20200714114817264"],"award-info":[{"award-number":["RCBS20200714114817264"]}]},{"name":"Guangdong Provincial Key Laboratory","award":["2020B121201001"],"award-info":[{"award-number":["2020B121201001"]}]},{"name":"Program for Guangdong Introducing Innovative and Entrepreneurial Teams","award":["2017ZT07X386"],"award-info":[{"award-number":["2017ZT07X386"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/tg.2022.3208324","type":"journal-article","created":{"date-parts":[[2022,9,21]],"date-time":"2022-09-21T19:31:11Z","timestamp":1663788671000},"page":"51-63","source":"Crossref","is-referenced-by-count":6,"title":["Lamarckian Platform: Pushing the Boundaries of Evolutionary Reinforcement Learning Toward Asynchronous Commercial Games"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8947-8913","authenticated-orcid":false,"given":"Hui","family":"Bai","sequence":"first","affiliation":[{"name":"Guangdong Key Laboratory of Brain-Inspired Intelligent Computation, Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}]},{"given":"Ruimin","family":"Shen","sequence":"additional","affiliation":[{"name":"NetEase Games AI Lab, Guangzhou, China"}]},{"given":"Yue","family":"Lin","sequence":"additional","affiliation":[{"name":"NetEase Games AI Lab, Guangzhou, China"}]},{"given":"Botian","family":"Xu","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Brain-Inspired Intelligent Computation, Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9410-8263","authenticated-orcid":false,"given":"Ran","family":"Cheng","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Brain-Inspired Intelligent Computation, Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref3","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lillicrap","year":"2016"},{"key":"ref4","first-page":"1621","article-title":"Learning to dispatch for job shop scheduling via deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref6","article-title":"OpenAI gym","author":"Brockman","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2877047"},{"key":"ref8","article-title":"Deepmind lab","author":"Beattie","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v15i1.5230"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3071162"},{"key":"ref11","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref13","article-title":"Evolution-guided policy gradient in reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Khadka","year":"2018"},{"key":"ref14","first-page":"3341","article-title":"Collaborative evolutionary reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Khadka","year":"2019,"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/466"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00077"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-020-0241-4"},{"key":"ref18","article-title":"Dopamine: A research framework for deep reinforcement learning","author":"Castro","year":"2018"},{"key":"ref19","article-title":"Tensorflow agents: Efficient batched reinforcement learning in tensorflow","author":"Hafner","year":"2017","journal-title":"CoRR"},{"key":"ref20","article-title":"Torchbeast: A pytorch platform for distributed RL","author":"Kttler","journal-title":"CoRR"},{"key":"ref21","first-page":"3053","article-title":"RLlib: Abstractions for distributed reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5232-5"},{"key":"ref23","first-page":"11","article-title":"Dynamic weights in multi-objective deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Abels","year":"2019"},{"key":"ref24","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref25","first-page":"1407","article-title":"IMPALA: Scalable distributed deep-rl with importance weighted actor-learner architectures","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Espeholt","year":"2018"},{"key":"ref26","article-title":"SEED RL: Scalable and efficient deep-RL with accelerated central inference","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Espeholt","year":"2020"},{"key":"ref27","first-page":"561","article-title":"Ray: A distributed framework for emerging AI applications","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Des. Implementation","author":"Moritz","year":"2018"},{"key":"ref28","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Mnih","year":"2016"},{"key":"ref29","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2006.1688438"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/1-84628-137-7_6"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/106365600568202"},{"key":"ref35","article-title":"Population based training of neural networks","author":"Jaderberg","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/BF00175354"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2016.00040"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/EVCO_a_00025"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref40","article-title":"Cem-RL: Combining evolutionary and gradient-based methods for policy search","author":"Pourchot","year":"2018"},{"key":"ref41","article-title":"Emergent coordination through competition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2019"},{"key":"ref42","article-title":"Evolving reinforcement learning algorithms","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Co-Reyes","year":"2021"},{"key":"ref43","first-page":"14610","article-title":"A generalized algorithm for multi-objective reinforcement learning and policy adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun","year":"2019"},{"key":"ref44","article-title":"TLeague: A framework for competitive self-play based distributed multi-agent reinforcement learning","author":"Sun","year":"2020"},{"key":"ref45","article-title":"Acme: A research framework for distributed reinforcement learning","author":"Hoffman","year":"2020"},{"key":"ref46","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Duan","year":"2016"},{"key":"ref47","first-page":"767","article-title":"SURREAL: Open-source reinforcement learning framework and robot manipulation benchmark","volume-title":"Proc. Conf. Robot Learn.","author":"Fan","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6216"},{"key":"ref49","article-title":"Malib: A parallel framework for population-based multi-agent reinforcement learning","author":"Zhou","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3049539"},{"key":"ref51","first-page":"621","article-title":"Towards playing full moba games with deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ye","year":"2020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/504087.504088"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1162\/106365603321828970"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1201\/9781315375229"},{"key":"ref55","article-title":"Illuminating search spaces by mapping elites","author":"Mouret","year":"2015"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2008.5035632"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8847966"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/10474491\/09897069.pdf?arnumber=9897069","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T20:11:36Z","timestamp":1714507896000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9897069\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":57,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tg.2022.3208324","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}