{"id":"https://openalex.org/W4414321910","doi":"https://doi.org/10.1109/tai.2025.3610590","title":"Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review","display_name":"Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review","publication_year":2025,"publication_date":"2025-09-18","ids":{"openalex":"https://openalex.org/W4414321910","doi":"https://doi.org/10.1109/tai.2025.3610590"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2025.3610590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3610590","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"},"type":"article","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/A5082520914","display_name":"Hossein Hassani","orcid":"https://orcid.org/0000-0003-3979-9166"},"institutions":[{"id":"https://openalex.org/I530967","display_name":"Toronto Metropolitan University","ror":"https://ror.org/05g13zd79","country_code":"CA","type":"education","lineage":["https://openalex.org/I530967"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hossein Hassani","raw_affiliation_strings":["Department of Mechanical, Industrial, and Mechatronics Engineering, Toronto Metropolitan University, Toronto, ON, Canada","Department of Mechanical, Industrial, and Mechatronics Engineering, Toronto Metropolitan University, Toronto, Canada"],"raw_orcid":"https://orcid.org/0000-0003-3979-9166","affiliations":[{"raw_affiliation_string":"Department of Mechanical, Industrial, and Mechatronics Engineering, Toronto Metropolitan University, Toronto, ON, Canada","institution_ids":["https://openalex.org/I530967"]},{"raw_affiliation_string":"Department of Mechanical, Industrial, and Mechatronics Engineering, Toronto Metropolitan University, Toronto, Canada","institution_ids":["https://openalex.org/I530967"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019275492","display_name":"Ehsan Hallaji","orcid":"https://orcid.org/0000-0002-9956-4003"},"institutions":[{"id":"https://openalex.org/I74413500","display_name":"University of Windsor","ror":"https://ror.org/01gw3d370","country_code":"CA","type":"education","lineage":["https://openalex.org/I74413500"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ehsan Hallaji","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, Canada","Department of Electrical and Computer Engineering, University of Windsor, Windsor, Canada"],"raw_orcid":"https://orcid.org/0000-0002-9956-4003","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, Canada","institution_ids":["https://openalex.org/I74413500"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Windsor, Windsor, Canada","institution_ids":["https://openalex.org/I74413500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019749887","display_name":"Roozbeh Razavi\u2010Far","orcid":"https://orcid.org/0000-0002-4330-3656"},"institutions":[{"id":"https://openalex.org/I106938459","display_name":"University of New Brunswick","ror":"https://ror.org/05nkf0n29","country_code":"CA","type":"education","lineage":["https://openalex.org/I106938459"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Roozbeh Razavi-Far","raw_affiliation_strings":["Faculty of Computer Science, University of New Brunswick, Fredericton, NB, Canada","Faculty of Computer Science, University of New Brunswick, Fredericton, Canada"],"raw_orcid":"https://orcid.org/0000-0002-4330-3656","affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, University of New Brunswick, Fredericton, NB, Canada","institution_ids":["https://openalex.org/I106938459"]},{"raw_affiliation_string":"Faculty of Computer Science, University of New Brunswick, Fredericton, Canada","institution_ids":["https://openalex.org/I106938459"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038291093","display_name":"Mehrdad Saif","orcid":"https://orcid.org/0000-0002-7587-4189"},"institutions":[{"id":"https://openalex.org/I74413500","display_name":"University of Windsor","ror":"https://ror.org/01gw3d370","country_code":"CA","type":"education","lineage":["https://openalex.org/I74413500"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mehrdad Saif","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, Canada","Department of Electrical and Computer Engineering, University of Windsor, Windsor, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7587-4189","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, Canada","institution_ids":["https://openalex.org/I74413500"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Windsor, Windsor, Canada","institution_ids":["https://openalex.org/I74413500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100412937","display_name":"Liang Lin","orcid":"https://orcid.org/0000-0003-2248-3755"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Lin","raw_affiliation_strings":["School of Computer Science, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2248-3755","affiliations":[{"raw_affiliation_string":"School of Computer Science, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2763,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95567862,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"7","issue":"4","first_page":"1819","last_page":"1834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.930899977684021,"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":0.930899977684021,"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/generalization","display_name":"Generalization","score":0.6782000064849854},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.36629998683929443},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.3125},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.30820000171661377},{"id":"https://openalex.org/keywords/calculus","display_name":"Calculus (dental)","score":0.267300009727478}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6782000064849854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46970000863075256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40860000252723694},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39570000767707825},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.3125},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C2777686260","wikidata":"https://www.wikidata.org/wiki/Q144037","display_name":"Calculus (dental)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2025.3610590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3610590","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":118,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1567876833","https://openalex.org/W1999874108","https://openalex.org/W2031571562","https://openalex.org/W2032558547","https://openalex.org/W2091565802","https://openalex.org/W2119717200","https://openalex.org/W2156869222","https://openalex.org/W2606378794","https://openalex.org/W2738975853","https://openalex.org/W2788862220","https://openalex.org/W2789734892","https://openalex.org/W2883109840","https://openalex.org/W2885265484","https://openalex.org/W2904814783","https://openalex.org/W2909906617","https://openalex.org/W2914702425","https://openalex.org/W2925005147","https://openalex.org/W2945642643","https://openalex.org/W2949913959","https://openalex.org/W2955238561","https://openalex.org/W2962737134","https://openalex.org/W2962744619","https://openalex.org/W2962845991","https://openalex.org/W2963079702","https://openalex.org/W2963184124","https://openalex.org/W2973229164","https://openalex.org/W2979229105","https://openalex.org/W2979766322","https://openalex.org/W3015685049","https://openalex.org/W3023586494","https://openalex.org/W3030346619","https://openalex.org/W3034815680","https://openalex.org/W3037606473","https://openalex.org/W3042729974","https://openalex.org/W3056678973","https://openalex.org/W3083921766","https://openalex.org/W3087191066","https://openalex.org/W3088310808","https://openalex.org/W3090612618","https://openalex.org/W3091362478","https://openalex.org/W3091471537","https://openalex.org/W3096831136","https://openalex.org/W3097470552","https://openalex.org/W3106649810","https://openalex.org/W3113358868","https://openalex.org/W3118300017","https://openalex.org/W3120623881","https://openalex.org/W3121683757","https://openalex.org/W3124922852","https://openalex.org/W3129586599","https://openalex.org/W3130441769","https://openalex.org/W3131283938","https://openalex.org/W3132473140","https://openalex.org/W3133214370","https://openalex.org/W3136506777","https://openalex.org/W3137303899","https://openalex.org/W3138984732","https://openalex.org/W3155402581","https://openalex.org/W3171912333","https://openalex.org/W3176646219","https://openalex.org/W3185580138","https://openalex.org/W3196896000","https://openalex.org/W3198359393","https://openalex.org/W3198999478","https://openalex.org/W3199435072","https://openalex.org/W3200276130","https://openalex.org/W3201683003","https://openalex.org/W3203504876","https://openalex.org/W3204171449","https://openalex.org/W3205260198","https://openalex.org/W3205598877","https://openalex.org/W3206106208","https://openalex.org/W3206282417","https://openalex.org/W3206393052","https://openalex.org/W3206938627","https://openalex.org/W3209078210","https://openalex.org/W3209562871","https://openalex.org/W3210179814","https://openalex.org/W3215168886","https://openalex.org/W4200538966","https://openalex.org/W4206024271","https://openalex.org/W4206392599","https://openalex.org/W4210491163","https://openalex.org/W4210882709","https://openalex.org/W4210909794","https://openalex.org/W4213206621","https://openalex.org/W4213376483","https://openalex.org/W4220889482","https://openalex.org/W4221020555","https://openalex.org/W4226029785","https://openalex.org/W4226440390","https://openalex.org/W4226518300","https://openalex.org/W4232512588","https://openalex.org/W4285189244","https://openalex.org/W4288391528","https://openalex.org/W4292289324","https://openalex.org/W4294936113","https://openalex.org/W4309669389","https://openalex.org/W4311416371","https://openalex.org/W4312403563","https://openalex.org/W4313136702","https://openalex.org/W4313142062","https://openalex.org/W4319831446","https://openalex.org/W4327571609","https://openalex.org/W4364374595","https://openalex.org/W4366483297","https://openalex.org/W4383112908","https://openalex.org/W4386702747","https://openalex.org/W4389667013","https://openalex.org/W4401559903","https://openalex.org/W4402435386","https://openalex.org/W4404201236","https://openalex.org/W4404727063","https://openalex.org/W4406018902","https://openalex.org/W4406160951","https://openalex.org/W7133211372","https://openalex.org/W7133240313"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}