{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:55:36Z","timestamp":1785858936564,"version":"3.56.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["N00014-18-1-2830"],"award-info":[{"award-number":["N00014-18-1-2830"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015599","name":"Toyota Research Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015599","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ECCS-2145134 CAREER Award"],"award-info":[{"award-number":["ECCS-2145134 CAREER Award"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2218759"],"award-info":[{"award-number":["CNS-2218759"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-2211542"],"award-info":[{"award-number":["CCF-2211542"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015599","name":"Toyota Research Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015599","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/tro.2022.3232300","type":"journal-article","created":{"date-parts":[[2023,1,19]],"date-time":"2023-01-19T18:58:08Z","timestamp":1674154688000},"page":"1801-1815","source":"Crossref","is-referenced-by-count":47,"title":["Maximum-Entropy Multi-Agent Dynamic Games: Forward and Inverse Solutions"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1045-4423","authenticated-orcid":false,"given":"Negar","family":"Mehr","sequence":"first","affiliation":[{"name":"Aerospace Engineering Department, University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0063-7445","authenticated-orcid":false,"given":"Mingyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4742-9192","authenticated-orcid":false,"given":"Maulik","family":"Bhatt","sequence":"additional","affiliation":[{"name":"Department of Aerospace Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7871-3663","authenticated-orcid":false,"given":"Mac","family":"Schwager","sequence":"additional","affiliation":[{"name":"Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9170-7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids.2011.6100856"},{"key":"ref15","article-title":"Forward and inverse methods in optimal control and dynamic game theory","author":"awasthi","year":"2019","journal-title":"Master's thesis"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917745980"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147924"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.029"},{"key":"ref11","first-page":"4572","article-title":"Generative adversarial imitation learning","author":"ho","year":"0","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref10","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","author":"finn","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref54","author":"cover","year":"2012","journal-title":"Elements of Information Theory"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2010.65"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.1206"},{"key":"ref19","article-title":"Multi-agent inverse reinforcement learning for zero-sum games","author":"lin","year":"2014"},{"key":"ref18","article-title":"Computational rationalization: The inverse equilibrium problem","author":"waugh","year":"2013"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912456319"},{"key":"ref50","first-page":"75","article-title":"Algorithms and computational techniques in differential dynamic programming","volume":"31","author":"yakowitz","year":"2012","journal-title":"Control Dyn Syst Adv Theory Appl"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907001"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/BF00925746"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341137"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197129"},{"key":"ref42","article-title":"Equivalence between policy gradients and soft Q-learning","author":"schulman","year":"2017"},{"key":"ref41","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume":"70","author":"haarnoja","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref44","author":"ba?ar","year":"1998","journal-title":"Dynamic Noncooperative Game Theory"},{"key":"ref43","article-title":"Reinforcement learning and control as probabilistic inference: Tutorial and review","author":"levine","year":"2018"},{"key":"ref49","first-page":"222","article-title":"Iterative linear quadratic regulator design for nonlinear biological movement systems","author":"li","year":"0","journal-title":"Proc ICINCO (1)"},{"key":"ref8","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"ng","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1115\/1.3653115"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref4","article-title":"Cooperative inverse reinforcement learning","volume":"29","author":"hadfield-menell","year":"2016","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref3","first-page":"475","article-title":"Continuous inverse optimal control with locally optimal examples","author":"levine","year":"0","journal-title":"Proc 29th Int Cof Int Conf Mach Learn"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref5","article-title":"Interaction dataset: An international, adversarial and cooperative motion dataset in interactive driving scenarios with semantic maps","author":"zhan","year":"2019"},{"key":"ref40","first-page":"829","article-title":"Learning complex neural network policies with trajectory optimization","author":"levine","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","first-page":"493","article-title":"Rational decision making in business organizations","volume":"69","author":"simon","year":"1979","journal-title":"Amer Econ Rev"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.2307\/1884852"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009905800005"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1006\/game.1995.1023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147489"},{"key":"ref30","article-title":"Inverse dynamic games based on maximum entropy inverse reinforcement learning","author":"inga","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1137\/070699652"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.030"},{"key":"ref2","article-title":"Modeling purposeful adaptive behavior with the principle of maximum causal entropy","author":"ziebart","year":"2010"},{"key":"ref1","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"ziebart","year":"0","journal-title":"Proc 23rd AAAI Conf Artif Intell"},{"key":"ref39","first-page":"1","article-title":"Guided policy search","author":"levine","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1111\/j.0347-0520.2004.00378.x"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/37"},{"key":"ref23","article-title":"Multi-agent generative adversarial imitation learning","volume":"31","author":"song","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1820676116"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029555"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11541"},{"key":"ref22","first-page":"7194","article-title":"Multi-agent adversarial inverse reinforcement learning","author":"yu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","article-title":"Modelling bounded rationality in multi-agent interactions by generalized recursive reasoning","author":"wen","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2017.08.2537"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3074880"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2017.08.2538"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/8860\/10144918\/10021943-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8860\/10144918\/10021943.pdf?arnumber=10021943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T18:59:23Z","timestamp":1687805963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10021943\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":54,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tro.2022.3232300","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"value":"1552-3098","type":"print"},{"value":"1941-0468","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}