{"id":"https://openalex.org/W3170828825","doi":"https://doi.org/10.3233/aise210096","title":"Inverse Reinforcement Learning Through Max-Margin Algorithm","display_name":"Inverse Reinforcement Learning Through Max-Margin Algorithm","publication_year":2021,"publication_date":"2021-06-14","ids":{"openalex":"https://openalex.org/W3170828825","doi":"https://doi.org/10.3233/aise210096","mag":"3170828825"},"language":"en","primary_location":{"id":"doi:10.3233/aise210096","is_oa":true,"landing_page_url":"https://doi.org/10.3233/aise210096","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/AISE210096","source":{"id":"https://openalex.org/S4210168452","display_name":"Ambient intelligence and smart environments","issn_l":"1875-4163","issn":["1875-4163","1875-4171"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ambient Intelligence and Smart Environments","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/AISE210096","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045580773","display_name":"Syed Ihtesham Hussain Shah","orcid":"https://orcid.org/0000-0002-6390-1864"},"institutions":[{"id":"https://openalex.org/I183638586","display_name":"Parthenope University of Naples","ror":"https://ror.org/05pcv4v03","country_code":"IT","type":"education","lineage":["https://openalex.org/I183638586"]},{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Syed Ihtesham Hussain Shah","raw_affiliation_strings":["Dept. of ICT and Engineering, University of Parthenope, Italy","Institute for high performance computing and networking (ICAR), National Research Council, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of ICT and Engineering, University of Parthenope, Italy","institution_ids":["https://openalex.org/I183638586"]},{"raw_affiliation_string":"Institute for high performance computing and networking (ICAR), National Research Council, Italy","institution_ids":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088137751","display_name":"Antonio Coronato","orcid":"https://orcid.org/0000-0001-8177-032X"},"institutions":[{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Antonio Coronato","raw_affiliation_strings":["Institute for high performance computing and networking (ICAR), National Research Council, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for high performance computing and networking (ICAR), National Research Council, Italy","institution_ids":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7033,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.87229142,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12288","display_name":"Optimization and Search Problems","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8367143869400024},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.8113206624984741},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6594687700271606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6541485786437988},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.58515465259552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5579222440719604},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.45386362075805664},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43478280305862427},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33337879180908203},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1571589708328247},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.058871179819107056}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8367143869400024},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.8113206624984741},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6594687700271606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6541485786437988},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.58515465259552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5579222440719604},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.45386362075805664},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43478280305862427},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33337879180908203},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1571589708328247},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.058871179819107056},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/aise210096","is_oa":true,"landing_page_url":"https://doi.org/10.3233/aise210096","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/AISE210096","source":{"id":"https://openalex.org/S4210168452","display_name":"Ambient intelligence and smart environments","issn_l":"1875-4163","issn":["1875-4163","1875-4171"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ambient Intelligence and Smart Environments","raw_type":"book-chapter"},{"id":"pmh:oai:zenodo.org:122107","is_oa":true,"landing_page_url":"https://www.openaccessrepository.it/record/122107","pdf_url":null,"source":{"id":"https://openalex.org/S4306402478","display_name":"INFM-OAR (INFN Catania)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210116497","host_organization_name":"Istituto Nazionale di Fisica Nucleare, Sezione di Catania","host_organization_lineage":["https://openalex.org/I4210116497"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":{"id":"doi:10.3233/aise210096","is_oa":true,"landing_page_url":"https://doi.org/10.3233/aise210096","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/AISE210096","source":{"id":"https://openalex.org/S4210168452","display_name":"Ambient intelligence and smart environments","issn_l":"1875-4163","issn":["1875-4163","1875-4171"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ambient Intelligence and Smart Environments","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1878189925","display_name":null,"funder_award_id":"ARS01 00900","funder_id":"https://openalex.org/F4320321873","funder_display_name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca"}],"funders":[{"id":"https://openalex.org/F4320321873","display_name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca","ror":"https://ror.org/0166hxq48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3170828825.pdf","grobid_xml":"https://content.openalex.org/works/W3170828825.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1752500127","https://openalex.org/W1757796397","https://openalex.org/W1906772730","https://openalex.org/W1984988829","https://openalex.org/W1999874108","https://openalex.org/W2051228319","https://openalex.org/W2061562262","https://openalex.org/W2062525454","https://openalex.org/W2082299845","https://openalex.org/W2085227190","https://openalex.org/W2107726111","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2129111104","https://openalex.org/W2151040408","https://openalex.org/W2155639879","https://openalex.org/W2165612525","https://openalex.org/W2169498096","https://openalex.org/W2212870508","https://openalex.org/W2257979135","https://openalex.org/W2277630443","https://openalex.org/W2566837261","https://openalex.org/W2619989803","https://openalex.org/W2754517384","https://openalex.org/W2809005670","https://openalex.org/W2899201912","https://openalex.org/W2899830387","https://openalex.org/W2909499846","https://openalex.org/W2938324248","https://openalex.org/W2963277051","https://openalex.org/W2963561234","https://openalex.org/W2964006217","https://openalex.org/W3012118145","https://openalex.org/W3086433273","https://openalex.org/W3090832565","https://openalex.org/W3099098707","https://openalex.org/W3099912664","https://openalex.org/W3120603942","https://openalex.org/W4214717370","https://openalex.org/W4298023569","https://openalex.org/W4298857966","https://openalex.org/W4320013936","https://openalex.org/W6637618640","https://openalex.org/W6637967152","https://openalex.org/W6676007687","https://openalex.org/W6684455146","https://openalex.org/W6684627452","https://openalex.org/W6718092244","https://openalex.org/W6744123322"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703","https://openalex.org/W41015297"],"abstract_inverted_index":{"Reinforcement":[0,46],"Learning":[1,47],"(RL)":[2],"methods":[3],"provide":[4],"a":[5,15,19,25,77],"solution":[6],"for":[7,29,76],"decision-making":[8],"problems":[9,33],"under":[10],"uncertainty.":[11],"An":[12],"agent":[13],"finds":[14],"suitable":[16],"policy":[17,88],"through":[18,58,108],"reward":[20,43,56,74,83,106],"function":[21,57,75,84],"by":[22,53],"interacting":[23],"with":[24],"dynamic":[26],"environment.":[27],"However,":[28],"complex":[30],"and":[31,40,104],"large":[32],"it":[34],"is":[35],"very":[36],"difficult":[37],"to":[38,71],"specify":[39],"tune":[41],"the":[42,55,73,86,109],"function.":[44],"Inverse":[45],"(IRL)":[48],"may":[49],"mitigate":[50],"this":[51,99],"problem":[52],"learning":[54],"expert":[59,113],"demonstrations.":[60],"This":[61],"work":[62],"exploits":[63],"an":[64],"IRL":[65],"method":[66,100,111],"named":[67],"Max-Margin":[68],"Algorithm":[69],"(MMA)":[70],"learn":[72],"robotic":[78],"navigation":[79],"problem.":[80],"The":[81],"learned":[82,105],"reveals":[85],"demonstrated":[87],"(expert":[89],"policy)":[90],"better":[91,102],"than":[92],"all":[93],"other":[94],"policies.":[95],"Results":[96],"show":[97],"that":[98],"has":[101],"convergence":[103],"functions":[107],"adopted":[110],"represents":[112],"behavior":[114],"more":[115],"efficiently.":[116]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}