{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T06:09:54Z","timestamp":1766297394414,"version":"3.48.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246087","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"7989-7996","source":"Crossref","is-referenced-by-count":1,"title":["Symmetry-Guided Multi-Agent Inverse Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yongkai","family":"Tian","sequence":"first","affiliation":[{"name":"Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yirong","family":"Qi","sequence":"additional","affiliation":[{"name":"Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Yu","sequence":"additional","affiliation":[{"name":"Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjun","family":"Wu","sequence":"additional","affiliation":[{"name":"Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Luo","sequence":"additional","affiliation":[{"name":"Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-36625-3_7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802212"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103905"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127434"},{"key":"ref5","article-title":"Inverse reward design","volume":"30","author":"Hadfield-Menell","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"Concrete problems in ai safety","year":"2016","author":"Amodei","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2010.65"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2017.2679115"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref11","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proceedings of the Seventeenth International Conference on Machine Learning","author":"Ng"},{"key":"ref12","first-page":"661","article-title":"Efficient reductions for imitation learning","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics","author":"Ross"},{"key":"ref13","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics","author":"Ross"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3395626"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-021-00314-5"},{"article-title":"Multiagent mdp homomorphic networks","volume-title":"International Conference on Learning Representations","author":"van der Pol","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230609"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA240741"},{"key":"ref19","article-title":"Multi-agent generative adversarial imitation learning","volume":"31","author":"Song","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref20","first-page":"7194","article-title":"Multi-agent adversarial inverse reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Yu"},{"article-title":"Scalable multiagent inverse reinforcement learning via actor-attention-critic","year":"2020","author":"Jeon","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM52615.2021.9669656"},{"key":"ref23","first-page":"1116","article-title":"Dec-airl: Decentralized adversarial irl for human-robot teaming","volume-title":"Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems","author":"Sengadu Suresh"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29709"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611035"},{"article-title":"Boosting multiagent reinforcement learning via permutation invariant and permutation equivariant networks","volume-title":"The Eleventh International Conference on Learning Representations","author":"Jianye","key":"ref26"},{"article-title":"Permutation invariant policy optimization for mean-field multiagent reinforcement learning: A principled approach","year":"2021","author":"Li","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/sym15030663"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref30","first-page":"7665","article-title":"Provably efficient learning of transferable rewards","volume-title":"International Conference on Machine Learning","author":"Metelli"},{"key":"ref31","first-page":"24611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.05.007"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.75.1226"},{"key":"ref34","article-title":"Near-optimal regret bounds for reinforcement learning","volume":"21","author":"Auer","year":"2008","journal-title":"Advances in neural information processing systems"},{"key":"ref35","first-page":"2701","article-title":"Why is posterior sampling better than optimism for reinforcement learning?","volume-title":"International conference on machine learning","author":"Osband"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246087.pdf?arnumber=11246087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:35:50Z","timestamp":1766061350000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246087\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246087","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}