{"id":"https://openalex.org/W4386193536","doi":"https://doi.org/10.1145/3616864","title":"Explainable Reinforcement Learning: A Survey and Comparative Review","display_name":"Explainable Reinforcement Learning: A Survey and Comparative Review","publication_year":2023,"publication_date":"2023-08-26","ids":{"openalex":"https://openalex.org/W4386193536","doi":"https://doi.org/10.1145/3616864"},"language":"en","primary_location":{"id":"doi:10.1145/3616864","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3616864","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616864","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"review","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3616864","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066795279","display_name":"Stephanie Milani","orcid":"https://orcid.org/0000-0003-1150-4418"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Stephanie Milani","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0003-1150-4418","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051795411","display_name":"Nicholay Topin","orcid":"https://orcid.org/0009-0006-5376-2801"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicholay Topin","raw_affiliation_strings":["Inpleo Inc., Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0009-0006-5376-2801","affiliations":[{"raw_affiliation_string":"Inpleo Inc., Pittsburgh, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088276691","display_name":"Manuela Veloso","orcid":"https://orcid.org/0000-0001-6738-238X"},"institutions":[{"id":"https://openalex.org/I2802755631","display_name":"Morgan Stanley (United States)","ror":"https://ror.org/00aphdz18","country_code":"US","type":"company","lineage":["https://openalex.org/I2802755631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manuela Veloso","raw_affiliation_strings":["J. P. Morgan AI Research, New York, USA","J. P. Morgan AI Research, United States"],"raw_orcid":"https://orcid.org/0000-0001-6738-238X","affiliations":[{"raw_affiliation_string":"J. P. Morgan AI Research, New York, USA","institution_ids":["https://openalex.org/I2802755631"]},{"raw_affiliation_string":"J. P. Morgan AI Research, United States","institution_ids":["https://openalex.org/I2802755631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061127138","display_name":"Fei Fang","orcid":"https://orcid.org/0000-0003-2256-8329"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Fang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0003-2256-8329","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5066795279"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":26.3379,"has_fulltext":true,"cited_by_count":155,"citation_normalized_percentile":{"value":0.99735806,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"56","issue":"7","first_page":"1","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9987999796867371,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9987999796867371,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996999979019165,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9815000295639038,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7935725450515747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7868649959564209},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.6577333807945251},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5402002930641174},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49465271830558777},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4157561659812927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4110737144947052},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32830750942230225},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.16362115740776062}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7935725450515747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7868649959564209},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.6577333807945251},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5402002930641174},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49465271830558777},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4157561659812927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4110737144947052},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32830750942230225},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.16362115740776062},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3616864","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3616864","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616864","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3616864","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3616864","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616864","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8100000023841858}],"awards":[{"id":"https://openalex.org/G2043895709","display_name":null,"funder_award_id":"W911NF-13-2-0045","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G3732666562","display_name":null,"funder_award_id":"W911NF-13","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G4321615664","display_name":"CAREER: Integrating Machine Learning with Game Theory for Multiagent Communication and Coordination","funder_award_id":"2046640","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5259331294","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G5979736433","display_name":null,"funder_award_id":"W911NF-13-2-0045 (ARL Cyber Security CRA)","funder_id":"https://openalex.org/F4320338456","funder_display_name":"DEVCOM Army Research Laboratory"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6911058591","display_name":null,"funder_award_id":"IIS-2046640","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8000996158","display_name":null,"funder_award_id":"W911NF-13-2-0045","funder_id":"https://openalex.org/F4320338456","funder_display_name":"DEVCOM Army Research Laboratory"},{"id":"https://openalex.org/G8727049869","display_name":null,"funder_award_id":"W911NF-13","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8763038417","display_name":null,"funder_award_id":"Cooperative Agreement Number W911NF-13-2-0045","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320315784","display_name":"U.S. Army Combat Capabilities Development Command Soldier Center","ror":"https://ror.org/02rdkx920"},{"id":"https://openalex.org/F4320333566","display_name":"National Defense Science and Engineering Graduate","ror":null},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"},{"id":"https://openalex.org/F4320338456","display_name":"DEVCOM Army Research Laboratory","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386193536.pdf","grobid_xml":"https://content.openalex.org/works/W4386193536.grobid-xml"},"referenced_works_count":172,"referenced_works":["https://openalex.org/W11104910","https://openalex.org/W1543281322","https://openalex.org/W1592847719","https://openalex.org/W1872493208","https://openalex.org/W1986014385","https://openalex.org/W1998937898","https://openalex.org/W1999874108","https://openalex.org/W2025587182","https://openalex.org/W2046622454","https://openalex.org/W2082345008","https://openalex.org/W2083782640","https://openalex.org/W2094837707","https://openalex.org/W2096285822","https://openalex.org/W2100495367","https://openalex.org/W2103581399","https://openalex.org/W2108281694","https://openalex.org/W2117629901","https://openalex.org/W2123199310","https://openalex.org/W2130000957","https://openalex.org/W2135316258","https://openalex.org/W2159111852","https://openalex.org/W2257979135","https://openalex.org/W2291986326","https://openalex.org/W2335959470","https://openalex.org/W2337392266","https://openalex.org/W2594164664","https://openalex.org/W2594336441","https://openalex.org/W2602856279","https://openalex.org/W2604382266","https://openalex.org/W2604394466","https://openalex.org/W2604738573","https://openalex.org/W2619383789","https://openalex.org/W2622408375","https://openalex.org/W2624731731","https://openalex.org/W2728455196","https://openalex.org/W2749807327","https://openalex.org/W2765204106","https://openalex.org/W2766447205","https://openalex.org/W2766736793","https://openalex.org/W2769421449","https://openalex.org/W2794566101","https://openalex.org/W2805516822","https://openalex.org/W2811104224","https://openalex.org/W2890141553","https://openalex.org/W2891340972","https://openalex.org/W2891830784","https://openalex.org/W2892841407","https://openalex.org/W2896457183","https://openalex.org/W2897798332","https://openalex.org/W2898632797","https://openalex.org/W2902538158","https://openalex.org/W2904939492","https://openalex.org/W2909102800","https://openalex.org/W2913668833","https://openalex.org/W2914584698","https://openalex.org/W2923762280","https://openalex.org/W2941205169","https://openalex.org/W2950892788","https://openalex.org/W2952298682","https://openalex.org/W2952561542","https://openalex.org/W2952927816","https://openalex.org/W2954503794","https://openalex.org/W2961374456","https://openalex.org/W2962702317","https://openalex.org/W2963095307","https://openalex.org/W2963262099","https://openalex.org/W2963324077","https://openalex.org/W2964164283","https://openalex.org/W2968461543","https://openalex.org/W2970447476","https://openalex.org/W2971538581","https://openalex.org/W2982057500","https://openalex.org/W2982316857","https://openalex.org/W2983753125","https://openalex.org/W2990984513","https://openalex.org/W2998004401","https://openalex.org/W2999614490","https://openalex.org/W2999803881","https://openalex.org/W3001365517","https://openalex.org/W3002769442","https://openalex.org/W3003997138","https://openalex.org/W3004798888","https://openalex.org/W3004940685","https://openalex.org/W3008110675","https://openalex.org/W3012229961","https://openalex.org/W3012502279","https://openalex.org/W3014924334","https://openalex.org/W3028689275","https://openalex.org/W3037614835","https://openalex.org/W3044916305","https://openalex.org/W3083829057","https://openalex.org/W3089895152","https://openalex.org/W3092043450","https://openalex.org/W3095702468","https://openalex.org/W3101038122","https://openalex.org/W3101438731","https://openalex.org/W3101981467","https://openalex.org/W3103946812","https://openalex.org/W3105162718","https://openalex.org/W3123348991","https://openalex.org/W3124373176","https://openalex.org/W3124922852","https://openalex.org/W3126044426","https://openalex.org/W3126321819","https://openalex.org/W3127561923","https://openalex.org/W3128395826","https://openalex.org/W3130234572","https://openalex.org/W3137125108","https://openalex.org/W3138819813","https://openalex.org/W3156365820","https://openalex.org/W3164011142","https://openalex.org/W3175186743","https://openalex.org/W3175871729","https://openalex.org/W3180541557","https://openalex.org/W3184543962","https://openalex.org/W3185645972","https://openalex.org/W3185816745","https://openalex.org/W3195577433","https://openalex.org/W3201595984","https://openalex.org/W3204551200","https://openalex.org/W3211095199","https://openalex.org/W3211658609","https://openalex.org/W3213728903","https://openalex.org/W4214717370","https://openalex.org/W4221152145","https://openalex.org/W4221153037","https://openalex.org/W4221159094","https://openalex.org/W4224043255","https://openalex.org/W4224225023","https://openalex.org/W4225265678","https://openalex.org/W4225533190","https://openalex.org/W4225674220","https://openalex.org/W4226054889","https://openalex.org/W4226088469","https://openalex.org/W4226165102","https://openalex.org/W4226211393","https://openalex.org/W4230750131","https://openalex.org/W4230846333","https://openalex.org/W4280584261","https://openalex.org/W4281610210","https://openalex.org/W4281788452","https://openalex.org/W4283382154","https://openalex.org/W4283721947","https://openalex.org/W4283737042","https://openalex.org/W4283787646","https://openalex.org/W4285090004","https://openalex.org/W4285674619","https://openalex.org/W4286850188","https://openalex.org/W4286891004","https://openalex.org/W4287100356","https://openalex.org/W4287659270","https://openalex.org/W4287750003","https://openalex.org/W4287869619","https://openalex.org/W4287871662","https://openalex.org/W4292779060","https://openalex.org/W4294619778","https://openalex.org/W4294964479","https://openalex.org/W4297821991","https://openalex.org/W4297897083","https://openalex.org/W4298235707","https://openalex.org/W4298857966","https://openalex.org/W4308092268","https://openalex.org/W4320870457","https://openalex.org/W4402843978","https://openalex.org/W6637967152","https://openalex.org/W6777449117","https://openalex.org/W6778883912","https://openalex.org/W6785279468","https://openalex.org/W6800751262","https://openalex.org/W6811049331","https://openalex.org/W6839204832","https://openalex.org/W6891886391"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894"],"abstract_inverted_index":{"Explainable":[0],"reinforcement":[1,31],"learning":[2,11,32,121],"(XRL)":[3],"is":[4,24],"an":[5],"emerging":[6],"subfield":[7],"of":[8,22,30,82,93],"explainable":[9],"machine":[10],"that":[12,87,109],"has":[13],"attracted":[14],"considerable":[15],"attention":[16],"in":[17,35,55,75,84],"recent":[18],"years.":[19],"The":[20],"goal":[21],"XRL":[23,107],"to":[25,133,149],"elucidate":[26],"the":[27,56,62,76,80,89,94,106,111],"decision-making":[28,37,91],"process":[29,122],"(RL)":[33],"agents":[34,51,63],"sequential":[36,90],"settings.":[38],"Equipped":[39],"with":[40],"this":[41,97,134],"information,":[42],"practitioners":[43],"can":[44],"better":[45],"understand":[46],"important":[47],"questions":[48],"about":[49],"RL":[50,112],"(especially":[52],"those":[53],"deployed":[54],"real":[57],"world),":[58],"such":[59],"as":[60],"what":[61],"will":[64],"do":[65],"and":[66,123,127,138,151],"why.":[67],"Despite":[68],"increased":[69],"interest,":[70],"there":[71],"exists":[72],"a":[73,85,101,153],"gap":[74],"literature":[77,108],"for":[78,104,140,155],"organizing":[79,105],"plethora":[81],"papers\u2014especially":[83],"way":[86],"centers":[88],"nature":[92],"problem.":[95],"In":[96],"survey,":[98],"we":[99],"propose":[100,115],"novel":[102],"taxonomy":[103],"prioritizes":[110],"setting.":[113],"We":[114,129,143],"three":[116],"high-level":[117],"categories:":[118],"feature":[119],"importance,":[120],"Markov":[124],"decision":[125],"process,":[126],"policy-level.":[128],"overview":[130],"techniques":[131],"according":[132],"taxonomy,":[135],"highlighting":[136],"challenges":[137],"opportunities":[139],"future":[141,156],"work.":[142,157],"conclude":[144],"by":[145],"using":[146],"these":[147],"gaps":[148],"motivate":[150],"outline":[152],"roadmap":[154]},"counts_by_year":[{"year":2026,"cited_by_count":26},{"year":2025,"cited_by_count":106},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}