{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T10:41:11Z","timestamp":1763116871850,"version":"3.37.3"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1109\/smc52423.2021.9658704","type":"proceedings-article","created":{"date-parts":[[2022,1,6]],"date-time":"2022-01-06T20:34:35Z","timestamp":1641501275000},"page":"3067-3074","source":"Crossref","is-referenced-by-count":2,"title":["Inverse Reinforcement Learning for Strategy Identification"],"prefix":"10.1109","author":[{"given":"Mark","family":"Rucker","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen","family":"Adams","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roy","family":"Hayes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter A.","family":"Beling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11541"},{"key":"ref10","first-page":"2097","article-title":"A cultural decision-making model for negotiation based on inverse reinforcement learning","author":"nouri","year":"2012","journal-title":"Proceedings of the 34th Annual Conference of the Cognitive Science Society"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858557"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cobeha.2019.04.010"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2017.8247872"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40988-2_3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006122"},{"key":"ref16","first-page":"16","article-title":"Inverse reinforcement learning for strategy extraction","author":"muelling","year":"2013","journal-title":"MLSA13–Proceedings of ‘Machine Learning and Data Mining for Sports Analytics’ workshop ECML\/PKDD 2013"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2015.1011684"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2014.6889878"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"article-title":"Stable baselines3","year":"2019","author":"raffin","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2819940"},{"key":"ref27","article-title":"Training goal recognition online from low-level inputs in an action-adventure game","volume":"5","author":"gold","year":"2010","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment"},{"journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming","year":"2014","author":"puterman","key":"ref3"},{"key":"ref6","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"ng","year":"2000","journal-title":"ICML"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2017.2679115"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915619772"},{"key":"ref7","first-page":"1","article-title":"An application of reinforcement learning to aerobatic helicopter flight","volume":"19","author":"abbeel","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3145814"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.01.003"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2009.5286483"},{"key":"ref20","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"ziebart","year":"2008","journal-title":"AAAI"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917722396"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2011.5990948"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11720","article-title":"Imitation learning via kernel mean embedding","volume":"32","author":"kim","year":"2018","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"article-title":"Human apprenticeship learning via kernel-based inverse reinforcement learning","year":"2020","author":"rucker","key":"ref23"},{"key":"ref26","article-title":"Using a recursive neural network to learn an agent’s decision model for plan recognition","author":"bisson","year":"2015","journal-title":"Twenty-Fourth International Joint Conference on Artificial Intelligence"},{"key":"ref25","article-title":"A generalized multidimensional evaluation framework for player goal recognition","author":"min","year":"2016","journal-title":"Artificial Intelligence for Interactive Digital Entertainment Conference"}],"event":{"name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","start":{"date-parts":[[2021,10,17]]},"location":"Melbourne, Australia","end":{"date-parts":[[2021,10,20]]}},"container-title":["2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9658572\/9658575\/09658704.pdf?arnumber=9658704","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T05:14:53Z","timestamp":1674364493000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9658704\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/smc52423.2021.9658704","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]}}}