{"id":"https://openalex.org/W2096871511","doi":"https://doi.org/10.1109/acc.2011.5990948","title":"Inverse reinforcement learning with Gaussian process","display_name":"Inverse reinforcement learning with Gaussian process","publication_year":2011,"publication_date":"2011-06-01","ids":{"openalex":"https://openalex.org/W2096871511","doi":"https://doi.org/10.1109/acc.2011.5990948","mag":"2096871511"},"language":"en","primary_location":{"id":"doi:10.1109/acc.2011.5990948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2011.5990948","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 American Control Conference","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/A5050966437","display_name":"Qifeng Qiao","orcid":"https://orcid.org/0009-0005-6765-568X"},"institutions":[{"id":"https://openalex.org/I4210116219","display_name":"Engineering Systems (United States)","ror":"https://ror.org/02qg60849","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116219"]},{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qifeng Qiao","raw_affiliation_strings":["Department of Systems and Information Engineeri, University of Virginia, Charlottesville, VA, USA","Department of Systems & Information Engineering, University of Virginia, Charlottesville, 22904, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems and Information Engineeri, University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I4210116219","https://openalex.org/I51556381"]},{"raw_affiliation_string":"Department of Systems & Information Engineering, University of Virginia, Charlottesville, 22904, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056670558","display_name":"Peter A. Beling","orcid":"https://orcid.org/0000-0003-2196-6982"},"institutions":[{"id":"https://openalex.org/I4210116219","display_name":"Engineering Systems (United States)","ror":"https://ror.org/02qg60849","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116219"]},{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter A. Beling","raw_affiliation_strings":["Department of Systems and Information Engineeri, University of Virginia, Charlottesville, VA, USA","Department of Systems & Information Engineering, University of Virginia, Charlottesville, 22904, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems and Information Engineeri, University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I4210116219","https://openalex.org/I51556381"]},{"raw_affiliation_string":"Department of Systems & Information Engineering, University of Virginia, Charlottesville, 22904, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1705,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.92596298,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"113","last_page":"118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9944999814033508,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9926000237464905,"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":0.5717642307281494},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5519855618476868},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5423259735107422},{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.5243252515792847},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.5115986466407776},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5000858306884766},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4644373059272766},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.45291611552238464},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.4244171380996704},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4127245545387268},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39062318205833435},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.3882172703742981},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.35874152183532715},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33355939388275146},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33032605051994324},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.2646314799785614}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5717642307281494},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5519855618476868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5423259735107422},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.5243252515792847},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.5115986466407776},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5000858306884766},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4644373059272766},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.45291611552238464},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.4244171380996704},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4127245545387268},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39062318205833435},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3882172703742981},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.35874152183532715},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33355939388275146},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33032605051994324},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.2646314799785614},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/acc.2011.5990948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2011.5990948","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 American Control Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.673.8855","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.673.8855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.nt.ntnu.no/users/skoge/prost/proceedings/acc11/data/papers/0970.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.754.6838","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.754.6838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1208.2112.pdf","raw_type":"text"},{"id":"mag:3145196196","is_oa":false,"landing_page_url":"http://yadda.icm.edu.pl/yadda/element/bwmeta1.element.ieee-000005990948","pdf_url":null,"source":{"id":"https://openalex.org/S4306417662","display_name":"American Control Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"American Control Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1559990548","https://openalex.org/W1591675293","https://openalex.org/W1746819321","https://openalex.org/W1965520710","https://openalex.org/W1999874108","https://openalex.org/W2061562262","https://openalex.org/W2102847492","https://openalex.org/W2113023245","https://openalex.org/W2116442740","https://openalex.org/W2341171179","https://openalex.org/W2530285197","https://openalex.org/W2912748147","https://openalex.org/W2950989964","https://openalex.org/W4211049957","https://openalex.org/W4230646247","https://openalex.org/W6633543754","https://openalex.org/W6676728370","https://openalex.org/W6677631742","https://openalex.org/W6728458309"],"related_works":["https://openalex.org/W2963058055","https://openalex.org/W2511279186","https://openalex.org/W4286859922","https://openalex.org/W2017957758","https://openalex.org/W3029748970","https://openalex.org/W3210763600","https://openalex.org/W3024650197","https://openalex.org/W2787723410","https://openalex.org/W4297928741","https://openalex.org/W1551416416"],"abstract_inverted_index":{"We":[0,17],"present":[1],"new":[2],"algorithms":[3],"for":[4,102],"inverse":[5,10],"reinforcement":[6],"learning":[7,123],"(IRL,":[8],"or":[9,49],"optimal":[11],"control)":[12],"in":[13,47,79,121],"convex":[14,27],"optimization":[15],"settings.":[16],"argue":[18],"that":[19,80],"finite-space":[20],"IRL":[21,78],"can":[22],"be":[23],"posed":[24],"as":[25],"a":[26,31,40,56,125],"quadratic":[28],"program":[29],"under":[30],"Bayesian":[32],"inference":[33],"framework":[34],"with":[35,45,108],"the":[36,86,89,96,130],"objective":[37],"of":[38,67,88,98,132],"maximum":[39],"posteriori":[41],"estimation.":[42],"To":[43],"deal":[44],"problems":[46],"large":[48],"even":[50],"infinite":[51],"state":[52],"space,":[53],"we":[54],"propose":[55],"Gaussian":[57],"process":[58],"model":[59],"and":[60,92,124],"use":[61],"preference":[62],"graphs":[63],"to":[64,77],"represent":[65],"observations":[66],"decision":[68],"trajectories.":[69],"Our":[70],"method":[71,117],"is":[72],"distinguished":[73],"from":[74],"other":[75],"approaches":[76],"it":[81,94],"makes":[82],"no":[83],"assumptions":[84],"about":[85],"form":[87],"reward":[90],"function":[91],"yet":[93],"retains":[95],"promise":[97],"computationally":[99],"manageable":[100],"implementations":[101],"potential":[103],"real-world":[104],"applications.":[105],"In":[106],"comparison":[107],"an":[109],"establish":[110],"algorithm":[111],"on":[112,129],"small-scale":[113],"numerical":[114],"problems,":[115],"our":[116],"demonstrated":[118],"better":[119],"accuracy":[120],"apprenticeship":[122],"more":[126],"robust":[127],"dependence":[128],"number":[131],"observations.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}