{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:49:53Z","timestamp":1771955393886,"version":"3.50.1"},"reference-count":21,"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"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247476","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"6071-6078","source":"Crossref","is-referenced-by-count":1,"title":["Cost Function Estimation Using Inverse Reinforcement Learning with Minimal Observations"],"prefix":"10.1109","author":[{"given":"Sarmad","family":"Mehrdad","sequence":"first","affiliation":[{"name":"New York University,Tandon School of Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Avadesh","family":"Meduri","sequence":"additional","affiliation":[{"name":"New York University,Tandon School of Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ludovic","family":"Righetti","sequence":"additional","affiliation":[{"name":"New York University,Tandon School of Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"2","key":"ref1","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"Ng","year":"2000","journal-title":"Icml"},{"key":"ref2","first-page":"1874","article-title":"Graph-based inverse optimal control for robot manipulation","volume":"15","author":"Byravan","year":"2015","journal-title":"Ijcai"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3143579"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/BIOROB.2018.8488045"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9170-7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2020.06.001"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10108-x"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143936"},{"key":"ref9","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Aaai","volume":"8","author":"Ziebart","year":"2008"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.106.620"},{"key":"ref11","first-page":"182","article-title":"Relative entropy inverse reinforcement learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings","author":"Boularias"},{"key":"ref12","article-title":"Continuous inverse optimal control with locally optimal examples","author":"Levine","year":"2012"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630743"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094679"},{"key":"ref15","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","volume-title":"International conference on machine learning","author":"Finn"},{"key":"ref16","article-title":"Inverse reinforcement learning with pi 2","volume-title":"The Snowbird Workshop","author":"Kalakrishnan"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196673"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980280"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SII.2019.8700380"},{"key":"ref20","article-title":"Stagewise implementations of sequential quadratic programming for model-predictive control","author":"Jordana","year":"2023","journal-title":"Subm. IEEE TRO"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"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\/11247476.pdf?arnumber=11247476","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:16:58Z","timestamp":1765520218000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247476\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247476","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}