{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T04:57:27Z","timestamp":1729659447543,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561771","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"12639-12645","source":"Crossref","is-referenced-by-count":2,"title":["Min-Max Entropy Inverse RL of Multiple Tasks"],"prefix":"10.1109","author":[{"given":"Saurabh","family":"Arora","sequence":"first","affiliation":[]},{"given":"Prashant","family":"Doshi","sequence":"additional","affiliation":[]},{"given":"Bikramjit","family":"Banerjee","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197393"},{"key":"ref11","first-page":"1","article-title":"Apprenticeship learning via inverse reinforcement learning","author":"abbeel","year":"2004","journal-title":"Twenty-first International Conference on Machine Learning (ICML)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1201\/b16018"},{"key":"ref13","first-page":"1287","article-title":"Bayesian nonparametric feature construction for inverse reinforcement learning","author":"choi","year":"2013","journal-title":"Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence ser IJCAI ’13"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1080\/10618600.2000.10474879","article-title":"Markov chain sampling methods for dirichlet process mixture models","volume":"9","author":"neal","year":"2000","journal-title":"Journal of Computational and Graphical Statistics"},{"key":"ref15","first-page":"2586","article-title":"Bayesian inverse reinforcement learning","author":"ramachandran","year":"2007","journal-title":"20th International Joint Conference on Artifical Intelligence (IJCAI)"},{"key":"ref16","first-page":"19","article-title":"Nonlinear inverse reinforcement learning with gaussian processes","author":"levine","year":"2011","journal-title":"24th International Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref17","first-page":"173","article-title":"Multi-robot inverse reinforcement learning under occlusion with interactions","author":"bogert","year":"2014","journal-title":"Proceedings of the 2014 International Conference on Autonomous Agents and Multi-agent Systems ser AAMAS ’14"},{"key":"ref18","first-page":"691","article-title":"Inverse reinforcement learning in partially observable environments","volume":"12","author":"choi","year":"2011","journal-title":"J Mach Learn Res"},{"article-title":"ultralytics\/yolov5: v3.1","year":"2020","author":"jocher","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1561\/2300000053"},{"key":"ref3","article-title":"A survey of inverse reinforcement learning: Challenges, methods and progress","author":"arora","year":"2018","journal-title":"CoRR"},{"key":"ref6","first-page":"305","article-title":"Nonparametric bayesian inverse reinforcement learning for multiple reward functions","author":"choi","year":"2012","journal-title":"25th International Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593745"},{"key":"ref8","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"3","author":"ziebart","year":"2008","journal-title":"23rd National Conference on Artificial Intelligence"},{"key":"ref7","first-page":"897","article-title":"Apprenticeship learning about multiple intentions","author":"babes-vroman","year":"2011","journal-title":"28th International Conference on Machine Learning (ICML)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279964"},{"key":"ref1","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"Seventeenth International Conference on Machine Learning"},{"article-title":"Multi-task maximum entropy inverse reinforcement learning","year":"2018","author":"gleave","key":"ref9"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561771.pdf?arnumber=9561771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T06:16:04Z","timestamp":1725948964000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561771","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}