{"id":"https://openalex.org/W3170234019","doi":"https://doi.org/10.3233/aise210097","title":"An Overview of Inverse Reinforcement Learning Techniques","display_name":"An Overview of Inverse Reinforcement Learning Techniques","publication_year":2021,"publication_date":"2021-06-14","ids":{"openalex":"https://openalex.org/W3170234019","doi":"https://doi.org/10.3233/aise210097","mag":"3170234019"},"language":"en","primary_location":{"id":"doi:10.3233/aise210097","is_oa":true,"landing_page_url":"https://doi.org/10.3233/aise210097","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/AISE210097","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/AISE210097","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/A5025157025","display_name":"Giuseppe De Pietro","orcid":"https://orcid.org/0000-0002-4675-5957"},"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":"Giuseppe De Pietro","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":4.6944,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.95485727,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.5946999788284302,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.5946999788284302,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11810","display_name":"Complex Systems and Decision Making","score":0.5547999739646912,"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"}},{"id":"https://openalex.org/T12659","display_name":"Innovation Diffusion and Forecasting","score":0.5390999913215637,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7995249032974243},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6634125709533691},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6624728441238403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6491754055023193},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5655052065849304},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5603099465370178},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.47191503643989563},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4364292323589325},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4270569384098053},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.21928200125694275},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13960126042366028},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07894372940063477}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7995249032974243},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6634125709533691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6624728441238403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6491754055023193},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5655052065849304},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5603099465370178},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.47191503643989563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4364292323589325},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4270569384098053},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.21928200125694275},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13960126042366028},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07894372940063477},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/aise210097","is_oa":true,"landing_page_url":"https://doi.org/10.3233/aise210097","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/AISE210097","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:122109","is_oa":true,"landing_page_url":"https://www.openaccessrepository.it/record/122109","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/aise210097","is_oa":true,"landing_page_url":"https://doi.org/10.3233/aise210097","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/AISE210097","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":0.800000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3170234019.pdf","grobid_xml":"https://content.openalex.org/works/W3170234019.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1521625446","https://openalex.org/W1591675293","https://openalex.org/W1975463331","https://openalex.org/W1985393656","https://openalex.org/W1999874108","https://openalex.org/W2034829409","https://openalex.org/W2062525454","https://openalex.org/W2069855531","https://openalex.org/W2082764616","https://openalex.org/W2098774185","https://openalex.org/W2107726111","https://openalex.org/W2133068870","https://openalex.org/W2212870508","https://openalex.org/W2597203481","https://openalex.org/W2804380964","https://openalex.org/W2899201912","https://openalex.org/W2899830387","https://openalex.org/W2938324248","https://openalex.org/W2946485478","https://openalex.org/W3008734873","https://openalex.org/W3012118145","https://openalex.org/W3035227524","https://openalex.org/W3086433273","https://openalex.org/W3090832565","https://openalex.org/W3099098707","https://openalex.org/W3099912664","https://openalex.org/W3109993998","https://openalex.org/W3120603942","https://openalex.org/W4214717370","https://openalex.org/W4252028749","https://openalex.org/W4253615028","https://openalex.org/W4298023569","https://openalex.org/W6723837491","https://openalex.org/W6751540476","https://openalex.org/W7075682605"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4225269853"],"abstract_inverted_index":{"In":[0],"decision-making":[1,21],"problems":[2,22,50],"reward":[3,37,64],"function":[4,38,65],"plays":[5],"an":[6,26,51,131],"important":[7],"role":[8],"in":[9,25,42,89,138,159],"finding":[10],"the":[11,36,92,102,139],"best":[12],"policy.":[13],"Reinforcement":[14,58],"Learning":[15,59,143],"(RL)":[16],"provides":[17],"a":[18,151],"solution":[19],"for":[20,39,74],"under":[23],"uncertainty":[24],"Intelligent":[27],"Environment":[28],"(IE).":[29],"However,":[30],"it":[31],"is":[32,61,66,72,128],"difficult":[33],"to":[34,78,120,129],"specify":[35],"RL":[40,54],"agents":[41],"large":[43],"and":[44,133,145],"complex":[45],"problems.":[46],"To":[47],"counter":[48],"these":[49],"extension":[52],"of":[53,83,87,91,96,104,125,136,141,157],"problem":[55],"named":[56],"Inverse":[57],"(IRL)":[60],"introduced,":[62],"where":[63],"learned":[67],"from":[68],"expert":[69],"demonstrations.":[70],"IRL":[71,113,137,158],"appealing":[73],"its":[75],"potential":[76],"use":[77],"build":[79],"autonomous":[80],"agents,":[81],"capable":[82],"modeling":[84],"others,":[85],"deprived":[86],"compromising":[88],"performance":[90],"task.":[93],"This":[94,109],"approach":[95],"learning":[97],"by":[98],"demonstrations":[99],"relies":[100],"on":[101],"framework":[103],"Markov":[105],"Decision":[106],"Process":[107],"(MDP).":[108],"article":[110],"elaborates":[111],"original":[112],"algorithms":[114],"along":[115],"with":[116],"their":[117],"close":[118],"variants":[119,156],"mitigate":[121],"challenges.":[122],"The":[123],"purpose":[124],"this":[126,160],"paper":[127],"highlight":[130],"overview":[132],"theoretical":[134],"background":[135],"field":[140],"Machine":[142],"(ML)":[144],"Artificial":[146],"Intelligence":[147],"(AI).":[148],"We":[149],"presented":[150],"brief":[152],"comparison":[153],"between":[154],"different":[155],"article.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2021-06-22T00:00:00"}
