{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:11:42Z","timestamp":1787011902607,"version":"build-2736575974"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,9]],"date-time":"2021-12-09T00:00:00Z","timestamp":1639008000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,9]],"date-time":"2021-12-09T00:00:00Z","timestamp":1639008000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100011347","name":"State Key Laboratory of Software Development Environment","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,9]]},"DOI":"10.1109\/bibm52615.2021.9669656","type":"proceedings-article","created":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T15:40:30Z","timestamp":1642174830000},"page":"274-279","source":"Crossref","is-referenced-by-count":14,"title":["Swarm Inverse Reinforcement Learning for Biological Systems"],"prefix":"10.1109","author":[{"given":"Xin","family":"Yu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering Beihang University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjun","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence Beihang University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pu","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering Beihang University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongkai","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering Beihang University,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref11","article-title":"Inverse reinforcement learning of bird flocking behavior","author":"pinsler","year":"2018","journal-title":"ICRA Swarms Workshop"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006122"},{"key":"ref13","article-title":"Dealing with non-stationarity in multi-agent deep reinforcement learning","author":"papoudakis","year":"2019","journal-title":"arXiv preprint arXiv 1906 10026"},{"key":"ref14","first-page":"7461","article-title":"Multi-agent generative adversarial imitation learning","author":"song","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"7194","article-title":"Multi-agent adversarial inverse reinforcement learning","author":"yu","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref16","first-page":"1413","article-title":"Inverse Reinforcement Learning in Swarm Systems","author":"\u0161o\u0161i?","year":"2017","journal-title":"Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref18","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1098\/rsfs.2012.0031"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2007.895842"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9671.2011.01261.x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0212044"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967824"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1007354"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.75.1226"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1561\/2300000053"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1006\/jtbi.2002.3065"},{"key":"ref20","first-page":"1989","article-title":"Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing","author":"christianos","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref21","first-page":"10707","article-title":"Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning","author":"christianos","year":"2020","journal-title":"Thirty-fourth Conference on Neural Information Processing Systems"},{"key":"ref24","article-title":"Proximal Policy Optimization Algorithms","author":"schulman","year":"0","journal-title":"arXiv 1707 06347"},{"key":"ref23","article-title":"Learning Robust Rewards with Adverserial Inverse Reinforcement Learning","author":"fu","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref25","first-page":"1","article-title":"Deep reinforcement learning for swarm systems","volume":"20","author":"h\u00fcttenrauch","year":"2019","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","location":"Houston, TX, USA","start":{"date-parts":[[2021,12,9]]},"end":{"date-parts":[[2021,12,12]]}},"container-title":["2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9669261\/9669139\/09669656.pdf?arnumber=9669656","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T17:21:40Z","timestamp":1655745700000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9669656\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,9]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/bibm52615.2021.9669656","relation":{},"subject":[],"published":{"date-parts":[[2021,12,9]]}}}