{"id":"https://openalex.org/W2904189787","doi":"https://doi.org/10.1609/aaai.v33i01.33012514","title":"Generation of Policy-Level Explanations for Reinforcement Learning","display_name":"Generation of Policy-Level Explanations for Reinforcement Learning","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2904189787","doi":"https://doi.org/10.1609/aaai.v33i01.33012514","mag":"2904189787"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33012514","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33012514","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4097/3975","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4097/3975","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051795411","display_name":"Nicholay Topin","orcid":"https://orcid.org/0009-0006-5376-2801"},"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":"Nicholay Topin","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088276691","display_name":"Manuela Veloso","orcid":"https://orcid.org/0000-0001-6738-238X"},"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":"Manuela Veloso","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051795411"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.399,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66132028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"33","issue":"01","first_page":"2514","last_page":"2521"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9950000047683716,"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":0.9922999739646912,"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":0.8994190096855164},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7308610677719116},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6983254551887512},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6967372894287109},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5904344320297241},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5657742023468018},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.563251256942749},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.557485818862915},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.555998682975769},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4768837094306946},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47096899151802063},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.45883670449256897},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.44960007071495056},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4494282603263855},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4439787268638611},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35134127736091614},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34547436237335205},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2274242639541626},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.20626536011695862},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1753406822681427},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.08264809846878052}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8994190096855164},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7308610677719116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6983254551887512},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6967372894287109},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5904344320297241},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5657742023468018},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.563251256942749},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.557485818862915},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.555998682975769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4768837094306946},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47096899151802063},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.45883670449256897},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.44960007071495056},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4494282603263855},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4439787268638611},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35134127736091614},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34547436237335205},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2274242639541626},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.20626536011695862},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1753406822681427},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.08264809846878052},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1609/aaai.v33i01.33012514","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33012514","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4097/3975","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1905.12044","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.12044","pdf_url":"https://arxiv.org/pdf/1905.12044","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2904189787","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1905.12044","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1905.12044","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.12044","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33012514","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33012514","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4097/3975","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2904189787.pdf","grobid_xml":"https://content.openalex.org/works/W2904189787.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W189498254","https://openalex.org/W2100788563","https://openalex.org/W2121863487","https://openalex.org/W2282821441","https://openalex.org/W2397240726","https://openalex.org/W2516809705","https://openalex.org/W2594164664","https://openalex.org/W2594336441","https://openalex.org/W2753415590","https://openalex.org/W2771145196","https://openalex.org/W2891830784","https://openalex.org/W2950708852","https://openalex.org/W2952901844","https://openalex.org/W2962851944","https://openalex.org/W2963149119","https://openalex.org/W6675028730","https://openalex.org/W6677916085","https://openalex.org/W6694177581","https://openalex.org/W6712173889"],"related_works":["https://openalex.org/W2952561542","https://openalex.org/W3189815242","https://openalex.org/W762189110","https://openalex.org/W3168711134","https://openalex.org/W2951895558","https://openalex.org/W2977937103","https://openalex.org/W854380377","https://openalex.org/W2187555640","https://openalex.org/W2579124618","https://openalex.org/W2810136497","https://openalex.org/W3176271731","https://openalex.org/W3171676778","https://openalex.org/W3197420008","https://openalex.org/W2183951929","https://openalex.org/W3205259120","https://openalex.org/W1784395471","https://openalex.org/W3037724138","https://openalex.org/W2607180594","https://openalex.org/W3171347509","https://openalex.org/W3092961465"],"abstract_inverted_index":{"Though":[0],"reinforcement":[1,137],"learning":[2,29,138],"has":[3],"greatly":[4],"benefited":[5],"from":[6],"the":[7,12,16,81,125,143,153,160],"incorporation":[8],"of":[9,18,39,49,64,83,109,147,155,162,174],"neural":[10],"networks,":[11],"inability":[13],"to":[14,92,171],"verify":[15],"correctness":[17],"such":[19],"systems":[20],"limits":[21],"their":[22],"use.":[23],"Current":[24],"work":[25],"in":[26,37,80,152,159,183],"explainable":[27],"deep":[28],"focuses":[30],"on":[31,123],"explaining":[32,46],"only":[33],"a":[34,47,71,90,102,107,172],"single":[35],"decision":[36],"terms":[38],"input":[40],"features,":[41],"making":[42],"it":[43],"unsuitable":[44],"for":[45,98],"sequence":[48],"decisions.":[50],"To":[51],"address":[52],"this":[53],"need,":[54],"we":[55,88,176],"introduce":[56],"Abstracted":[57,95,187],"Policy":[58,96,188],"Graphs,":[59],"which":[60,190],"are":[61,121],"Markov":[62],"chains":[63],"abstract":[65],"states.":[66],"This":[67],"representation":[68],"concisely":[69],"summarizes":[70],"policy":[72],"so":[73],"that":[74,142,178],"individual":[75],"decisions":[76],"can":[77],"be":[78],"explained":[79],"context":[82],"expected":[84],"future":[85],"transitions.":[86],"Additionally,":[87],"propose":[89],"method":[91,131,149,170,180],"generate":[93],"these":[94,195],"Graphs":[97,189],"deterministic":[99],"policies":[100],"given":[101],"learned":[103],"value":[104,126],"function":[105,127],"and":[106,157,185],"set":[108],"observed":[110],"transitions,":[111,164],"potentially":[112],"off-policy":[113],"transitions":[114],"used":[115],"during":[116],"training.":[117],"Since":[118],"no":[119],"restrictions":[120],"placed":[122],"how":[124],"is":[128,132,150],"generated,":[129],"our":[130,148,169,179],"compatible":[133],"with":[134],"many":[135],"existing":[136],"methods.":[139],"We":[140],"prove":[141],"worst-case":[144],"time":[145],"complexity":[146],"quadratic":[151],"number":[154,161],"features":[156],"linear":[158],"provided":[163],"O(|F|2|tr":[165],"samples|).":[166],"By":[167],"applying":[168],"family":[173],"domains,":[175],"show":[177],"scales":[181],"well":[182],"practice":[184],"produces":[186],"reliably":[191],"capture":[192],"relationships":[193],"within":[194],"domains.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}