{"id":"https://openalex.org/W3107531409","doi":"https://doi.org/10.1109/ssci47803.2020.9308391","title":"Revisiting Maximum Entropy Inverse Reinforcement Learning: New Perspectives and Algorithms","display_name":"Revisiting Maximum Entropy Inverse Reinforcement Learning: New Perspectives and Algorithms","publication_year":2020,"publication_date":"2020-12-01","ids":{"openalex":"https://openalex.org/W3107531409","doi":"https://doi.org/10.1109/ssci47803.2020.9308391","mag":"3107531409"},"language":"en","primary_location":{"id":"doi:10.1109/ssci47803.2020.9308391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci47803.2020.9308391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2012.00889","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091885274","display_name":"Aaron Snoswell","orcid":"https://orcid.org/0000-0003-0960-0144"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]},{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Aaron J. Snoswell","raw_affiliation_strings":["School of Information Technology and Electrical Engineering, The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"School of Information Technology and Electrical Engineering, The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911","https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010900748","display_name":"Surya P. N. Singh","orcid":"https://orcid.org/0000-0001-8112-4547"},"institutions":[{"id":"https://openalex.org/I4210161447","display_name":"Intuitive Surgical (United States)","ror":"https://ror.org/05g2n4m79","country_code":"US","type":"company","lineage":["https://openalex.org/I4210161447"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Surya P. N. Singh","raw_affiliation_strings":["Intuitive Surgical, Sunnyvale, USA"],"affiliations":[{"raw_affiliation_string":"Intuitive Surgical, Sunnyvale, USA","institution_ids":["https://openalex.org/I4210161447"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100536933","display_name":"Nan Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Nan Ye","raw_affiliation_strings":["School of Mathematics and Physics, The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and Physics, The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091885274"],"corresponding_institution_ids":["https://openalex.org/I160993911","https://openalex.org/I165143802"],"apc_list":null,"apc_paid":null,"fwci":0.6857,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.7747571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"241","last_page":"249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9872999787330627,"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":0.9872999787330627,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9620000123977661,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9602000117301941,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.7391481399536133},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6451838612556458},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.5753951072692871},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5645451545715332},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5597518682479858},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4710302948951721},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4667758047580719},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.45050883293151855},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.44551563262939453},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.42902588844299316},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4180935323238373},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4116842746734619},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4004718065261841},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2620733380317688}],"concepts":[{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.7391481399536133},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6451838612556458},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.5753951072692871},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5645451545715332},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5597518682479858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4710302948951721},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4667758047580719},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.45050883293151855},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.44551563262939453},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.42902588844299316},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4180935323238373},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4116842746734619},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4004718065261841},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2620733380317688},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ssci47803.2020.9308391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci47803.2020.9308391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2012.00889","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.00889","pdf_url":"https://arxiv.org/pdf/2012.00889","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2012.00889","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.00889","pdf_url":"https://arxiv.org/pdf/2012.00889","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W64088143","https://openalex.org/W1594849649","https://openalex.org/W1777239053","https://openalex.org/W1994648061","https://openalex.org/W1999874108","https://openalex.org/W2020609518","https://openalex.org/W2098774185","https://openalex.org/W2133068870","https://openalex.org/W2137813581","https://openalex.org/W2147544021","https://openalex.org/W2147880316","https://openalex.org/W2155098712","https://openalex.org/W2245493112","https://openalex.org/W2290104316","https://openalex.org/W2566467060","https://openalex.org/W2744369598","https://openalex.org/W2766610320","https://openalex.org/W2963508354","https://openalex.org/W2963590100","https://openalex.org/W3027397596","https://openalex.org/W3037207827","https://openalex.org/W3120740533","https://openalex.org/W4394666657","https://openalex.org/W6634004297","https://openalex.org/W6638088447","https://openalex.org/W6674884181","https://openalex.org/W6679958247","https://openalex.org/W6681478256","https://openalex.org/W6696380822"],"related_works":["https://openalex.org/W2105321464","https://openalex.org/W2887774187","https://openalex.org/W2388220555","https://openalex.org/W1554844486","https://openalex.org/W3048739257","https://openalex.org/W1665563134","https://openalex.org/W2963604926","https://openalex.org/W2199957582","https://openalex.org/W2033178790","https://openalex.org/W2035799335"],"abstract_inverted_index":{"We":[0,37,113,192],"provide":[1,114,193],"new":[2,204],"perspectives":[3],"and":[4,75,79,99,119,123,206,214],"inference":[5,97,125],"algorithms":[6,98,207],"for":[7,86,109],"Maximum":[8],"Entropy":[9,77],"(MaxEnt)":[10],"Inverse":[11],"Reinforcement":[12],"Learning":[13],"(IRL),":[14],"which":[15],"provides":[16],"a":[17,22,40,47,69,82,92,137,160,184],"principled":[18],"method":[19],"to":[20,81,116,157,174,183,211],"find":[21],"most":[23],"non-committal":[24],"reward":[25,35,170],"function":[26],"consistent":[27,34],"with":[28,198],"given":[29],"expert":[30],"demonstrations,":[31],"among":[32],"many":[33],"functions.":[36],"first":[38],"present":[39,120],"generalized":[41],"MaxEnt":[42,62,73,88,219],"formulation":[43],"based":[44],"on":[45],"minimizing":[46],"KL-divergence":[48],"instead":[49],"of":[50,60,72,95,152,216],"maximizing":[51],"an":[52,121,149,194],"entropy.":[53],"This":[54],"improves":[55,169],"the":[56,61,87,106,111,144,175,199,217],"previous":[57],"heuristic":[58],"derivation":[59],"IRL":[63,74,89,220],"model":[64],"(for":[65],"stochastic":[66],"MDPs),":[67],"allows":[68],"unified":[70],"view":[71],"Relative":[76],"IRL,":[78],"leads":[80],"model-free":[83],"learning":[84,110,171],"algorithm":[85,128,154,168,180],"model.":[90,112,221],"Second,":[91],"careful":[93],"review":[94],"existing":[96],"implementations":[100],"showed":[101],"that":[102,165],"they":[103],"approximately":[104],"compute":[105],"marginals":[107],"required":[108],"examples":[115],"illustrate":[117],"this,":[118],"efficient":[122],"exact":[124,167],"algorithm.":[126],"Our":[127,203],"can":[129],"handle":[130],"variable":[131],"length":[132,147],"demonstrations;":[133],"in":[134,143],"addition,":[135],"while":[136],"basic":[138],"version":[139,151],"takes":[140],"time":[141],"quadratic":[142],"maximum":[145],"demonstration":[146],"L,":[148],"improved":[150],"this":[153,156],"reduces":[155],"linear":[158],"using":[159],"padding":[161],"trick.":[162],"Experiments":[163],"show":[164],"our":[166,179],"as":[172],"compared":[173],"approximate":[176],"ones.":[177],"Furthermore,":[178],"scales":[181],"up":[182],"large,":[185],"real-world":[186],"dataset":[187],"involving":[188],"driver":[189],"behaviour":[190],"forecasting.":[191],"optimized":[195],"implementation":[196],"compatible":[197],"OpenAI":[200],"Gym":[201],"interface.":[202],"insight":[205],"could":[208],"possibly":[209],"lead":[210],"further":[212],"interest":[213],"exploration":[215],"original":[218]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}