{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:33:08Z","timestamp":1730255588885,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610814","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"272-278","source":"Crossref","is-referenced-by-count":0,"title":["Phasic Diversity Optimization for Population-Based Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Jingcheng","family":"Jiang","sequence":"first","affiliation":[{"name":"Dalian University of Technology,Key Laboratory of Social Computing and Cognitive Intelligence,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiyin","family":"Piao","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Electronics and Information,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Fu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,Key Laboratory of Social Computing and Cognitive Intelligence,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihang","family":"Hao","sequence":"additional","affiliation":[{"name":"Yangzhou Collaborative Innovation Research Institute Co., Ltd,Yangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanlu","family":"Jiang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,Key Laboratory of Social Computing and Cognitive Intelligence,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziqi","family":"Wei","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Yang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,Key Laboratory of Social Computing and Cognitive Intelligence,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Population based training of neural networks","year":"2017","author":"Jaderberg","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3449639.3459304"},{"key":"ref3","first-page":"51","article-title":"Diverse auto-curriculum is critical for successful real-world multiagent learning systems","author":"Yang","year":"2021","journal-title":"AAMAS \u201921"},{"journal-title":"Neuroevolution is a competitive alternative to reinforcement learning for skill discovery","year":"2022","author":"Chalumeau","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1561\/2200000044"},{"key":"ref6","first-page":"18050","article-title":"Effective diversity in population based reinforcement learning","volume":"33","author":"Parker-Holder","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Evolutionary diversity optimization with clustering-based selection for reinforcement learning","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022","author":"Wang","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2307\/2332286"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"journal-title":"Illuminating search spaces by mapping elites","year":"2015","author":"Mouret","key":"ref10"},{"article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"7th International Conference on Learning Representations","author":"Eysenbach","key":"ref11"},{"article-title":"Discovering diverse multi-agent strategic behavior via reward randomization","volume-title":"9th International Conference on Learning Representations","author":"Tang","key":"ref12"},{"key":"ref13","first-page":"7204","article-title":"Trajectory diversity for zero-shot coordination","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Lupu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i5.25758"},{"key":"ref15","first-page":"5923","article-title":"Diversity-inducing policy gradient: Using maximum mean discrepancy to find a set of diverse policies","volume-title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019","author":"Masood"},{"article-title":"Continuously discovering novel strategies via reward-switching policy optimization","volume-title":"International Conference on Learning Representations","author":"Zhou","key":"ref16"},{"key":"ref17","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proceedings of the 33nd International Conference on Machine Learning","volume":"48","author":"Mnih"},{"key":"ref18","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Haarnoja"},{"key":"ref19","first-page":"10510","article-title":"Diversity-driven exploration strategy for deep reinforcement learning","author":"Hong","year":"2018","journal-title":"Advances in Neural Information Processing Systems 31"},{"article-title":"Population-guided parallel policy search for reinforcement learning","volume-title":"8th International Conference on Learning Representations","author":"Jung","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3512290.3528845"},{"key":"ref22","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Fujimoto"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2961426"},{"key":"ref24","article-title":"Reinforcement learning based air combat maneuver generation","volume":"abs\/2201.05528","author":"\u00d6zbek","year":"2022","journal-title":"CoRR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.2514\/6.2023-1077"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119285"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08784-7"},{"journal-title":"Hindsight experience replay","year":"2017","author":"Andrychowicz","key":"ref28"},{"key":"ref29","first-page":"7445","article-title":"Learning to score behaviors for guided policy optimization","volume-title":"Proceedings of the 37th International Conference on Machine Learning","volume":"119","author":"Pacchiano"},{"journal-title":"Wasserstein GAN","year":"2017","author":"Arjovsky","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-030718-104938"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"journal-title":"Openai gym","year":"2016","author":"Brockman","key":"ref34"},{"key":"ref35","first-page":"2020","article-title":"Phasic policy gradient","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Cobbe"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2024,5,13]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610814.pdf?arnumber=10610814","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:56:23Z","timestamp":1723269383000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610814\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610814","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}