{"id":"https://openalex.org/W2891830784","doi":"https://doi.org/10.1145/3278721.3278776","title":"Transparency and Explanation in Deep Reinforcement Learning Neural Networks","display_name":"Transparency and Explanation in Deep Reinforcement Learning Neural Networks","publication_year":2018,"publication_date":"2018-12-27","ids":{"openalex":"https://openalex.org/W2891830784","doi":"https://doi.org/10.1145/3278721.3278776","mag":"2891830784"},"language":"en","primary_location":{"id":"doi:10.1145/3278721.3278776","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3278721.3278776","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3278721.3278776","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3278721.3278776","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109292369","display_name":"Rahul Iyer","orcid":null},"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":"Rahul Iyer","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032963335","display_name":"Yuezhang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuezhang Li","raw_affiliation_strings":["Google Inc., Mountain View, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, PA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084355106","display_name":"Huao Li","orcid":"https://orcid.org/0000-0002-0027-615X"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huao Li","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057603259","display_name":"Michael Lewis","orcid":"https://orcid.org/0000-0002-1013-9482"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Lewis","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101711875","display_name":"Ramitha Sundar","orcid":null},"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":"Ramitha Sundar","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087505541","display_name":"Katia Sycara","orcid":"https://orcid.org/0000-0001-5635-1406"},"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":"Katia Sycara","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.677,"has_fulltext":true,"cited_by_count":138,"citation_normalized_percentile":{"value":0.97466131,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"144","last_page":"150"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994999766349792,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994999766349792,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/transparency","display_name":"Transparency (behavior)","score":0.8544726371765137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7957282066345215},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7877700328826904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6828404068946838},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.6563154458999634},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6068472862243652},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5107705593109131},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.501051664352417},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4606831669807434},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4272688329219818},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4223196506500244},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33297792077064514},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1588960886001587},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08037060499191284}],"concepts":[{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.8544726371765137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7957282066345215},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7877700328826904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6828404068946838},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.6563154458999634},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6068472862243652},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5107705593109131},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.501051664352417},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4606831669807434},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4272688329219818},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4223196506500244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33297792077064514},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1588960886001587},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08037060499191284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3278721.3278776","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3278721.3278776","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3278721.3278776","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3278721.3278776","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3278721.3278776","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3278721.3278776","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G6803236541","display_name":null,"funder_award_id":"FA9550-15-1-0442","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2891830784.pdf","grobid_xml":"https://content.openalex.org/works/W2891830784.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W117178103","https://openalex.org/W154669480","https://openalex.org/W234809696","https://openalex.org/W1849277567","https://openalex.org/W1976570622","https://openalex.org/W2070986762","https://openalex.org/W2097117768","https://openalex.org/W2110171129","https://openalex.org/W2119717200","https://openalex.org/W2120480077","https://openalex.org/W2124175081","https://openalex.org/W2145339207","https://openalex.org/W2158698691","https://openalex.org/W2162651730","https://openalex.org/W2163605009","https://openalex.org/W2169393322","https://openalex.org/W2282821441","https://openalex.org/W2312609093","https://openalex.org/W2321972046","https://openalex.org/W2491179239","https://openalex.org/W2786344118","https://openalex.org/W2952072685","https://openalex.org/W2952523895","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W4321442002","https://openalex.org/W2015265939","https://openalex.org/W2284072287","https://openalex.org/W2611067230","https://openalex.org/W2480201319","https://openalex.org/W2387706296","https://openalex.org/W2155788121","https://openalex.org/W4235469518","https://openalex.org/W362492756","https://openalex.org/W2890345561"],"abstract_inverted_index":{"Autonomous":[0],"AI":[1],"systems":[2,21],"will":[3],"be":[4,23,30,44,179],"entering":[5],"human":[6,193],"society":[7],"in":[8,85,102,104,116,121,181],"the":[9,27,34,38,41,55,153,156,172],"near":[10],"future":[11],"to":[12,22,32,50,162,195],"provide":[13,163],"services":[14],"and":[15,25,58,73,136,176,192],"work":[16,101],"alongside":[17],"humans.":[18],"For":[19],"those":[20],"accepted":[24],"trusted,":[26],"users":[28],"should":[29,43],"able":[31],"understand":[33],"reasoning":[35],"process":[36],"of":[37,54,158,165,168,174],"system,":[39],"i.e.":[40],"system":[42],"transparent.":[45],"System":[46],"transparency":[47,103],"enables":[48],"humans":[49],"form":[51],"coherent":[52],"explanations":[53,175],"system's":[56],"decisions":[57],"actions.":[59],"Transparency":[60],"is":[61],"important":[62],"not":[63],"only":[64],"for":[65,70,155],"user":[66],"trust,":[67],"but":[68],"also":[69],"software":[71],"debugging":[72],"certification.":[74],"In":[75,95,129],"recent":[76],"years,":[77],"Deep":[78,105],"Neural":[79],"Networks":[80,108],"have":[81,112],"made":[82],"great":[83],"advances":[84],"multiple":[86],"application":[87],"areas.":[88],"However,":[89],"deep":[90,147,184],"neural":[91],"networks":[92,111],"are":[93],"opaque.":[94],"this":[96,130],"paper,":[97,131],"we":[98,132],"report":[99],"on":[100],"Reinforcement":[106],"Learning":[107],"(DRLN).":[109],"Such":[110],"been":[113],"extremely":[114],"successful":[115],"accurately":[117],"learning":[118,149,186],"action":[119],"control":[120],"image":[122],"input":[123],"domains,":[124],"such":[125],"as":[126],"Atari":[127],"games.":[128],"propose":[133],"a":[134],"novel":[135],"general":[137],"method":[138],"that":[139],"(a)":[140],"incorporates":[141],"explicit":[142],"object":[143],"recognition":[144],"processing":[145],"into":[146],"reinforcement":[148,185],"models,":[150],"(b)":[151],"forms":[152],"basis":[154],"development":[157],"\"object":[159],"saliency":[160],"maps\",":[161],"visualization":[164],"internal":[166],"states":[167],"DRLNs,":[169],"thus":[170],"enabling":[171],"formation":[173],"(c)":[177],"can":[178],"incorporated":[180],"any":[182],"existing":[183],"framework.":[187],"We":[188],"present":[189],"computational":[190],"results":[191],"experiments":[194],"evaluate":[196],"our":[197],"approach.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}