{"id":"https://openalex.org/W4408954824","doi":"https://doi.org/10.1007/s00521-025-11100-0","title":"Advances and applications in inverse reinforcement learning: a comprehensive review","display_name":"Advances and applications in inverse reinforcement learning: a comprehensive review","publication_year":2025,"publication_date":"2025-03-26","ids":{"openalex":"https://openalex.org/W4408954824","doi":"https://doi.org/10.1007/s00521-025-11100-0"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-025-11100-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11100-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11100-0.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11100-0.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047794545","display_name":"Saurabh Deshpande","orcid":"https://orcid.org/0000-0002-1813-9735"},"institutions":[{"id":"https://openalex.org/I244572783","display_name":"Symbiosis International University","ror":"https://ror.org/005r2ww51","country_code":"IN","type":"education","lineage":["https://openalex.org/I244572783"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Saurabh Deshpande","raw_affiliation_strings":["Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, Maharashtra, 412115, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, Maharashtra, 412115, India","institution_ids":["https://openalex.org/I244572783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068767089","display_name":"Rahee Walambe","orcid":"https://orcid.org/0000-0003-1745-5231"},"institutions":[{"id":"https://openalex.org/I244572783","display_name":"Symbiosis International University","ror":"https://ror.org/005r2ww51","country_code":"IN","type":"education","lineage":["https://openalex.org/I244572783"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Rahee Walambe","raw_affiliation_strings":["Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, Maharashtra, 412115, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, Maharashtra, 412115, India","institution_ids":["https://openalex.org/I244572783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077770842","display_name":"Ketan Kotecha","orcid":"https://orcid.org/0000-0003-2653-3780"},"institutions":[{"id":"https://openalex.org/I126527374","display_name":"Peoples' Friendship University of Russia","ror":"https://ror.org/02dn9h927","country_code":"RU","type":"education","lineage":["https://openalex.org/I126527374"]},{"id":"https://openalex.org/I244572783","display_name":"Symbiosis International University","ror":"https://ror.org/005r2ww51","country_code":"IN","type":"education","lineage":["https://openalex.org/I244572783"]}],"countries":["IN","RU"],"is_corresponding":false,"raw_author_name":"Ketan Kotecha","raw_affiliation_strings":["RUDN University (Peoples\u2019 Friendship University of Russia), 6 Miklukho-Maklaya Str., Moscow, Russian Federation, 117198","Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, Maharashtra, 412115, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RUDN University (Peoples\u2019 Friendship University of Russia), 6 Miklukho-Maklaya Str., Moscow, Russian Federation, 117198","institution_ids":["https://openalex.org/I126527374"]},{"raw_affiliation_string":"Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, Maharashtra, 412115, India","institution_ids":["https://openalex.org/I244572783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070517330","display_name":"Ganeshsree Selvachandran","orcid":"https://orcid.org/0000-0001-7161-2109"},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]},{"id":"https://openalex.org/I244572783","display_name":"Symbiosis International University","ror":"https://ror.org/005r2ww51","country_code":"IN","type":"education","lineage":["https://openalex.org/I244572783"]}],"countries":["IN","MY"],"is_corresponding":true,"raw_author_name":"Ganeshsree Selvachandran","raw_affiliation_strings":["School of Business, Monash University Malaysia, Jalan Lagoon Selatan, Bandar Sunway, 47500, Subang Jaya, Selangor, Malaysia","Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, Maharashtra, 412115, India"],"raw_orcid":"https://orcid.org/0000-0001-7161-2109","affiliations":[{"raw_affiliation_string":"School of Business, Monash University Malaysia, Jalan Lagoon Selatan, Bandar Sunway, 47500, Subang Jaya, Selangor, Malaysia","institution_ids":["https://openalex.org/I11662577"]},{"raw_affiliation_string":"Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, Maharashtra, 412115, India","institution_ids":["https://openalex.org/I244572783"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087542455","display_name":"Ajith Abraham","orcid":"https://orcid.org/0000-0002-0169-6738"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ajith Abraham","raw_affiliation_strings":["School of Artificial Intelligence, Sai University, Paiyanur, Chennai, Tamil Nadu, 603104, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Sai University, Paiyanur, Chennai, Tamil Nadu, 603104, India","institution_ids":["https://openalex.org/I4210164862"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068767089","https://openalex.org/A5070517330"],"corresponding_institution_ids":["https://openalex.org/I11662577","https://openalex.org/I244572783"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":12.2365,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.98322767,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"37","issue":"17","first_page":"11071","last_page":"11123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986000061035156,"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":0.9986000061035156,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9817000031471252,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9800000190734863,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.8520469665527344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6406843662261963},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6186168789863586},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5445119142532349},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5118066668510437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4354466497898102},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3620795011520386},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.338525652885437},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1866600513458252},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.06355446577072144},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06301751732826233},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.05910450220108032}],"concepts":[{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.8520469665527344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6406843662261963},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6186168789863586},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5445119142532349},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5118066668510437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4354466497898102},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3620795011520386},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.338525652885437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1866600513458252},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.06355446577072144},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06301751732826233},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.05910450220108032}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00521-025-11100-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11100-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11100-0.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s00521-025-11100-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11100-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11100-0.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6862396409","display_name":null,"funder_award_id":"202256-2-000","funder_id":"https://openalex.org/F4320329913","funder_display_name":"RUDN University"}],"funders":[{"id":"https://openalex.org/F4320320971","display_name":"Monash University","ror":"https://ror.org/02bfwt286"},{"id":"https://openalex.org/F4320329913","display_name":"RUDN University","ror":"https://ror.org/02dn9h927"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408954824.pdf"},"referenced_works_count":166,"referenced_works":["https://openalex.org/W52822972","https://openalex.org/W195596278","https://openalex.org/W1527702126","https://openalex.org/W1533707276","https://openalex.org/W1543204590","https://openalex.org/W1566073559","https://openalex.org/W1567876833","https://openalex.org/W1574859627","https://openalex.org/W1574928409","https://openalex.org/W1626398438","https://openalex.org/W1652033540","https://openalex.org/W1799240622","https://openalex.org/W1815701967","https://openalex.org/W1889081078","https://openalex.org/W1929981607","https://openalex.org/W1974964983","https://openalex.org/W1977828796","https://openalex.org/W1988580225","https://openalex.org/W1999874108","https://openalex.org/W2021472139","https://openalex.org/W2031067035","https://openalex.org/W2031571562","https://openalex.org/W2051944318","https://openalex.org/W2057134775","https://openalex.org/W2062525454","https://openalex.org/W2069195348","https://openalex.org/W2071771048","https://openalex.org/W2074739868","https://openalex.org/W2096871511","https://openalex.org/W2100401322","https://openalex.org/W2109910161","https://openalex.org/W2115450697","https://openalex.org/W2115579991","https://openalex.org/W2116774898","https://openalex.org/W2119785746","https://openalex.org/W2124394479","https://openalex.org/W2133068870","https://openalex.org/W2135822894","https://openalex.org/W2140251882","https://openalex.org/W2142972908","https://openalex.org/W2151296058","https://openalex.org/W2156163138","https://openalex.org/W2158362042","https://openalex.org/W2187006281","https://openalex.org/W2250303055","https://openalex.org/W2264897026","https://openalex.org/W2277630443","https://openalex.org/W2281287867","https://openalex.org/W2287850282","https://openalex.org/W2290104316","https://openalex.org/W2338865890","https://openalex.org/W2344349469","https://openalex.org/W2396489399","https://openalex.org/W2396863940","https://openalex.org/W2396881363","https://openalex.org/W2470789286","https://openalex.org/W2519586580","https://openalex.org/W2562989799","https://openalex.org/W2566837261","https://openalex.org/W2620965402","https://openalex.org/W2734346390","https://openalex.org/W2749796268","https://openalex.org/W2753088790","https://openalex.org/W2757337920","https://openalex.org/W2765199760","https://openalex.org/W2783154620","https://openalex.org/W2783922473","https://openalex.org/W2789386227","https://openalex.org/W2802441085","https://openalex.org/W2883483516","https://openalex.org/W2891385160","https://openalex.org/W2895649888","https://openalex.org/W2898191412","https://openalex.org/W2898621619","https://openalex.org/W2903821316","https://openalex.org/W2909499846","https://openalex.org/W2909906617","https://openalex.org/W2910123761","https://openalex.org/W2910170770","https://openalex.org/W2910375409","https://openalex.org/W2914112028","https://openalex.org/W2924637980","https://openalex.org/W2925561801","https://openalex.org/W2937671098","https://openalex.org/W2939047085","https://openalex.org/W2942735643","https://openalex.org/W2945642643","https://openalex.org/W2946233467","https://openalex.org/W2949500778","https://openalex.org/W2953259115","https://openalex.org/W2963508354","https://openalex.org/W2963762522","https://openalex.org/W2963797805","https://openalex.org/W2963800628","https://openalex.org/W2970197073","https://openalex.org/W2974892902","https://openalex.org/W2980087597","https://openalex.org/W2982059251","https://openalex.org/W2984552550","https://openalex.org/W2991138762","https://openalex.org/W2992382489","https://openalex.org/W2996663904","https://openalex.org/W2997519688","https://openalex.org/W2999304763","https://openalex.org/W3003652570","https://openalex.org/W3003808276","https://openalex.org/W3004041605","https://openalex.org/W3005141941","https://openalex.org/W3007958381","https://openalex.org/W3008929485","https://openalex.org/W3009702296","https://openalex.org/W3017835356","https://openalex.org/W3033639178","https://openalex.org/W3035574168","https://openalex.org/W3035679825","https://openalex.org/W3037606473","https://openalex.org/W3040321451","https://openalex.org/W3040858909","https://openalex.org/W3045019238","https://openalex.org/W3049574859","https://openalex.org/W3081056513","https://openalex.org/W3082495008","https://openalex.org/W3086102299","https://openalex.org/W3089891697","https://openalex.org/W3092940675","https://openalex.org/W3093988073","https://openalex.org/W3101805180","https://openalex.org/W3103078873","https://openalex.org/W3104181348","https://openalex.org/W3106415912","https://openalex.org/W3114224083","https://openalex.org/W3114759637","https://openalex.org/W3118456481","https://openalex.org/W3120991176","https://openalex.org/W3121683757","https://openalex.org/W3126081202","https://openalex.org/W3126222328","https://openalex.org/W3130800560","https://openalex.org/W3130972395","https://openalex.org/W3132973354","https://openalex.org/W3138984732","https://openalex.org/W3144867668","https://openalex.org/W3153999169","https://openalex.org/W3162904728","https://openalex.org/W3176912151","https://openalex.org/W3186019740","https://openalex.org/W3208231292","https://openalex.org/W4206748476","https://openalex.org/W4206941460","https://openalex.org/W4210909794","https://openalex.org/W4232512588","https://openalex.org/W4243052851","https://openalex.org/W4287728403","https://openalex.org/W4289543323","https://openalex.org/W4294201702","https://openalex.org/W4297349373","https://openalex.org/W4299401133","https://openalex.org/W4302377903","https://openalex.org/W4388562378","https://openalex.org/W4392877780","https://openalex.org/W4394666657","https://openalex.org/W4405023998","https://openalex.org/W6756615331","https://openalex.org/W6759637383","https://openalex.org/W6763056879","https://openalex.org/W6784242007"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Abstract":[0],"Reinforcement":[1],"learning,":[2,152],"characterized":[3],"by":[4,43,111],"trial-and-error":[5],"learning":[6,38,141],"and":[7,54,86,90,113,122,139,155,166,180,185],"delayed":[8],"rewards,":[9],"is":[10,21,28,106,126,142],"central":[11],"to":[12,147,183],"decision-making":[13],"processes.":[14],"Its":[15],"core":[16],"component,":[17],"the":[18,70,91,114,135,160,187],"reward":[19,45],"function,":[20],"traditionally":[22],"handcrafted,":[23],"but":[24],"designing":[25],"these":[26],"functions":[27,46],"often":[29],"challenging":[30],"or":[31],"impossible":[32],"in":[33,74,96,119,133,150],"real-world":[34],"scenarios.":[35],"Inverse":[36],"reinforcement":[37],"(IRL)":[39],"addresses":[40],"this":[41,171],"issue":[42],"extracting":[44],"from":[47],"expert":[48,60],"demonstrations,":[49],"facilitating":[50],"optimal":[51],"policy":[52],"derivation":[53],"offering":[55],"a":[56,175],"deeper":[57],"understanding":[58],"of":[59,93,103,116,131,163],"behavior.":[61],"This":[62],"comprehensive":[63],"review":[64,172],"focuses":[65],"on":[66],"three":[67],"key":[68],"aspects:":[69],"diverse":[71],"methodologies":[72],"employed":[73],"IRL,":[75],"its":[76,145],"wide-ranging":[77],"applications":[78,108],"across":[79],"fields":[80],"such":[81],"as":[82,174],"robotics,":[83],"autonomous":[84],"vehicles,":[85],"human":[87,138],"intent":[88],"analysis,":[89],"importance":[92],"curated":[94],"datasets":[95,118],"advancing":[97],"IRL":[98,104,132,164],"research.":[99],"A":[100],"structured":[101],"analysis":[102],"techniques":[105],"provided,":[107],"are":[109],"categorized":[110],"domain,":[112],"role":[115],"benchmark":[117],"evaluating":[120],"performance":[121],"guiding":[123],"future":[124,169],"developments":[125],"emphasized.":[127],"The":[128],"unique":[129],"value":[130],"bridging":[134],"gap":[136],"between":[137],"artificial":[140],"highlighted,":[143],"demonstrating":[144],"potential":[146],"unlock":[148],"advancements":[149],"machine":[151],"decision":[153],"making,":[154],"explainable":[156],"AI.":[157],"By":[158],"summarizing":[159],"current":[161],"state":[162],"research":[165],"advocating":[167],"for":[168,178],"directions,":[170],"serves":[173],"valuable":[176],"resource":[177],"researchers":[179],"practitioners":[181],"seeking":[182],"explore":[184],"advance":[186],"field.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}