{"id":"https://openalex.org/W4416750809","doi":"https://doi.org/10.1109/iros60139.2025.11247476","title":"Cost Function Estimation Using Inverse Reinforcement Learning with Minimal Observations","display_name":"Cost Function Estimation Using Inverse Reinforcement Learning with Minimal Observations","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750809","doi":"https://doi.org/10.1109/iros60139.2025.11247476"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010767992","display_name":"Sarmad Mehrdad","orcid":"https://orcid.org/0000-0001-5313-9493"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarmad Mehrdad","raw_affiliation_strings":["New York University,Tandon School of Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,Tandon School of Engineering,USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035427970","display_name":"Avadesh Meduri","orcid":"https://orcid.org/0000-0001-7742-3130"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Avadesh Meduri","raw_affiliation_strings":["New York University,Tandon School of Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,Tandon School of Engineering,USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026007843","display_name":"Ludovic Righetti","orcid":"https://orcid.org/0000-0002-6458-9112"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ludovic Righetti","raw_affiliation_strings":["New York University,Tandon School of Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,Tandon School of Engineering,USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6071","last_page":"6078"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5906999707221985,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5906999707221985,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.23720000684261322,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.013700000010430813,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5198000073432922},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.45910000801086426},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4528999924659729},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.42340001463890076},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4142000079154968},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.39489999413490295},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.38679999113082886},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.38350000977516174}],"concepts":[{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5583999752998352},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5220999717712402},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5198000073432922},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5148000121116638},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.42340001463890076},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3912999927997589},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.33309999108314514},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30889999866485596},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2574999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1994648061","https://openalex.org/W2019965290","https://openalex.org/W2032558547","https://openalex.org/W2037997802","https://openalex.org/W2155098712","https://openalex.org/W2158782408","https://openalex.org/W2169498096","https://openalex.org/W2897806808","https://openalex.org/W2906487027","https://openalex.org/W3037298378","https://openalex.org/W3081791272","https://openalex.org/W4210909794","https://openalex.org/W4214584936"],"related_works":[],"abstract_inverted_index":{"We":[0,106],"present":[1],"an":[2,37,112],"iterative":[3],"inverse":[4],"reinforcement":[5],"learning":[6],"algorithm":[7,60,85],"to":[8,35,49,56,121,132,139],"infer":[9],"optimal":[10,113],"cost":[11,44,80],"functions":[12],"in":[13,89,143],"continuous":[14],"spaces.":[15],"Based":[16],"on":[17,74],"a":[18,27,33,99],"popular":[19],"maximum":[20],"entropy":[21],"criteria,":[22],"our":[23,59,128],"approach":[24],"iteratively":[25],"finds":[26],"weight":[28],"improvement":[29],"step":[30,39],"and":[31],"proposes":[32],"method":[34,129],"find":[36],"appropriate":[38],"size":[40],"that":[41],"ensures":[42],"learned":[43],"function":[45,72,81],"features":[46],"remain":[47],"similar":[48,57],"the":[50,64,70,75,79,84,90,136],"demonstrated":[51],"trajectory":[52],"features.":[53],"In":[54,93],"contrast":[55],"approaches,":[58],"can":[61],"individually":[62],"tune":[63],"effectiveness":[65],"of":[66,78,117,127,135],"each":[67],"observation":[68],"for":[69],"partition":[71],"based":[73],"current":[76],"estimate":[77],"parameters,":[82],"guiding":[83],"towards":[86],"better":[87],"estimates":[88],"following":[91],"iterations.":[92],"addition,":[94],"it":[95],"does":[96],"not":[97],"need":[98],"large":[100],"sample":[101,108],"set,":[102],"enabling":[103],"faster":[104],"learning.":[105],"generate":[107],"trajectories":[109],"by":[110],"solving":[111],"control":[114],"problem":[115],"instead":[116],"random":[118],"sampling,":[119],"leading":[120],"more":[122],"informative":[123],"trajectories.":[124],"The":[125],"performance":[126],"is":[130],"compared":[131],"two":[133],"state":[134],"art":[137],"algorithms":[138],"demonstrate":[140],"its":[141],"benefits":[142],"several":[144],"simulated":[145],"environments.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}