{"id":"https://openalex.org/W3165647017","doi":"https://doi.org/10.1109/cog52621.2021.9618999","title":"Interactive Explanations: Diagnosis and Repair of Reinforcement Learning Based Agent Behaviors","display_name":"Interactive Explanations: Diagnosis and Repair of Reinforcement Learning Based Agent Behaviors","publication_year":2021,"publication_date":"2021-08-17","ids":{"openalex":"https://openalex.org/W3165647017","doi":"https://doi.org/10.1109/cog52621.2021.9618999","mag":"3165647017"},"language":"en","primary_location":{"id":"doi:10.1109/cog52621.2021.9618999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9618999","pdf_url":null,"source":{"id":"https://openalex.org/S4363608335","display_name":"2021 IEEE Conference on Games (CoG)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Conference on Games (CoG)","raw_type":"proceedings-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/A5028316887","display_name":"Christian Arzate Cruz","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Christian Arzate Cruz","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102743150","display_name":"Takeo Igarashi","orcid":"https://orcid.org/0000-0002-5495-6441"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeo Igarashi","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028316887"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.377,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.57487381,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9972000122070312,"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":0.9904999732971191,"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/computer-science","display_name":"Computer science","score":0.8131904602050781},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8122594356536865},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.6501652002334595},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5725234746932983},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4533608853816986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42754632234573364},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07771658897399902}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8131904602050781},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8122594356536865},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6501652002334595},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5725234746932983},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4533608853816986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42754632234573364},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07771658897399902},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog52621.2021.9618999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9618999","pdf_url":null,"source":{"id":"https://openalex.org/S4363608335","display_name":"2021 IEEE Conference on Games (CoG)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W2087634802","https://openalex.org/W2116533103","https://openalex.org/W2129659607","https://openalex.org/W2140584963","https://openalex.org/W2157922094","https://openalex.org/W2594336441","https://openalex.org/W2611884151","https://openalex.org/W2785955089","https://openalex.org/W2792893218","https://openalex.org/W2884552039","https://openalex.org/W2887663741","https://openalex.org/W2890809352","https://openalex.org/W2896215772","https://openalex.org/W2901707424","https://openalex.org/W2902729397","https://openalex.org/W2925554728","https://openalex.org/W2948380112","https://openalex.org/W2955877667","https://openalex.org/W2962891854","https://openalex.org/W2963367210","https://openalex.org/W2964915587","https://openalex.org/W2972018816","https://openalex.org/W2975349924","https://openalex.org/W2976108375","https://openalex.org/W2983662313","https://openalex.org/W2988345863","https://openalex.org/W3039116038","https://openalex.org/W3088918749","https://openalex.org/W3093908578","https://openalex.org/W3094236223","https://openalex.org/W3094604473","https://openalex.org/W3097926736","https://openalex.org/W3104514174","https://openalex.org/W3126466933","https://openalex.org/W3176079729","https://openalex.org/W6638088447","https://openalex.org/W6747554467","https://openalex.org/W6756274953","https://openalex.org/W6760732153","https://openalex.org/W6762257688","https://openalex.org/W6769847552","https://openalex.org/W6783697459","https://openalex.org/W6842212927"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2076061571","https://openalex.org/W2106552856","https://openalex.org/W1987513656","https://openalex.org/W2072376847","https://openalex.org/W2089013912"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"techniques":[2],"successfully":[3],"generate":[4],"convincing":[5],"agent":[6],"behaviors,":[7],"but":[8],"it":[9,76],"is":[10,25,27,74,122,174],"still":[11],"difficult":[12],"to":[13,17,34,42,94,105,129,137,141],"tailor":[14],"the":[15,32,36,40,85,87,95,98,106,109,116,120,130,144,158,166],"behavior":[16,37,103],"align":[18],"with":[19],"a":[20,28,50,64,78,134,139,155],"user's":[21],"specific":[22],"preferences.":[23],"What":[24],"missing":[26],"communication":[29,65,80],"method":[30,53,73,153],"for":[31,39],"system":[33],"explain":[35,90],"and":[38,84,97,124,143,165,178],"user":[41],"repair":[43],"it.":[44],"In":[45,113],"this":[46,71,114],"paper,":[47],"we":[48],"present":[49],"novel":[51],"interaction":[52,72],"that":[54,75,132,169],"uses":[55],"interactive":[56,111,171],"explanations":[57],"using":[58,108],"templates":[59],"of":[60,70,119,157],"natural":[61],"language":[62],"as":[63],"method.":[66],"The":[67],"main":[68],"advantage":[69],"enables":[77],"two-way":[79],"channel":[81],"between":[82],"users":[83,99,125],"agent;":[86],"bot":[88,107,121,131,180],"can":[89,100,126],"its":[91],"thinking":[92,117],"procedure":[93,118],"users,":[96],"communicate":[101],"their":[102],"preferences":[104],"same":[110],"explanations.":[112],"manner,":[115],"transparent,":[123],"provide":[127],"corrections":[128],"include":[133],"suggested":[135],"action":[136],"take,":[138],"goal":[140],"achieve,":[142],"reasons":[145],"behind":[146],"these":[147],"decisions.":[148],"We":[149],"tested":[150],"our":[151,170],"proposed":[152],"in":[154],"clone":[156],"video":[159],"game":[160],"named":[161],"Super":[162],"Mario":[163],"Bros.,":[164],"results":[167],"demonstrate":[168],"explanation":[172],"approach":[173],"effective":[175],"at":[176],"diagnosing":[177],"repairing":[179],"behaviors.":[181]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}