{"id":"https://openalex.org/W3089368496","doi":"https://doi.org/10.1587/transinf.2019edp7170","title":"Towards Interpretable Reinforcement Learning with State Abstraction Driven by External Knowledge","display_name":"Towards Interpretable Reinforcement Learning with State Abstraction Driven by External Knowledge","publication_year":2020,"publication_date":"2020-09-30","ids":{"openalex":"https://openalex.org/W3089368496","doi":"https://doi.org/10.1587/transinf.2019edp7170","mag":"3089368496"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2019edp7170","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7170","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/10/E103.D_2019EDP7170/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/10/E103.D_2019EDP7170/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069965217","display_name":"Nicolas Bougie","orcid":"https://orcid.org/0000-0001-9856-0038"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nicolas BOUGIE","raw_affiliation_strings":["National Institute of Informatics","Sokendai, The Graduate University for Advanced Studies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"Sokendai, The Graduate University for Advanced Studies","institution_ids":["https://openalex.org/I200475212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081854769","display_name":"Ryutaro Ichise","orcid":"https://orcid.org/0000-0001-8474-0150"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryutaro ICHISE","raw_affiliation_strings":["National Institute of Informatics","Sokendai, The Graduate University for Advanced Studies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"Sokendai, The Graduate University for Advanced Studies","institution_ids":["https://openalex.org/I200475212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5215,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73281314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"E103.D","issue":"10","first_page":"2143","last_page":"2153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973000288009644,"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":0.9973000288009644,"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":0.9973000288009644,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9959999918937683,"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/interpretability","display_name":"Interpretability","score":0.9054991006851196},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8779202699661255},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8611449003219604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.715854823589325},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6807453632354736},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5897036790847778},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5654690861701965},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5601908564567566},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5351579785346985},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5136986970901489},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.49622756242752075},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.47359851002693176},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4516810178756714}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9054991006851196},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8779202699661255},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8611449003219604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.715854823589325},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6807453632354736},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5897036790847778},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5654690861701965},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5601908564567566},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5351579785346985},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5136986970901489},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.49622756242752075},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.47359851002693176},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4516810178756714},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2019edp7170","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7170","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/10/E103.D_2019EDP7170/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2019edp7170","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7170","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/10/E103.D_2019EDP7170/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3089368496.pdf","grobid_xml":"https://content.openalex.org/works/W3089368496.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1499408472","https://openalex.org/W1557517019","https://openalex.org/W1757796397","https://openalex.org/W1998026388","https://openalex.org/W2089561656","https://openalex.org/W2097797606","https://openalex.org/W2106004777","https://openalex.org/W2111691418","https://openalex.org/W2113913482","https://openalex.org/W2121092017","https://openalex.org/W2124175081","https://openalex.org/W2125283600","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2150593711","https://openalex.org/W2154384352","https://openalex.org/W2154997814","https://openalex.org/W2155007355","https://openalex.org/W2155632266","https://openalex.org/W2169209873","https://openalex.org/W2171960770","https://openalex.org/W2173248099","https://openalex.org/W2521274174","https://openalex.org/W2572816092","https://openalex.org/W2736601468","https://openalex.org/W2774982397","https://openalex.org/W2796284132","https://openalex.org/W2797527950","https://openalex.org/W2798338638","https://openalex.org/W2811507977","https://openalex.org/W2896183040","https://openalex.org/W2901174038","https://openalex.org/W2919115771","https://openalex.org/W2963016445","https://openalex.org/W3020831056","https://openalex.org/W3041202696","https://openalex.org/W3139377883","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W4390569940","https://openalex.org/W2888392564","https://openalex.org/W4361193272","https://openalex.org/W4319993887","https://openalex.org/W4297789176","https://openalex.org/W2768346313","https://openalex.org/W2963249138","https://openalex.org/W2998594699","https://openalex.org/W4388585741"],"abstract_inverted_index":{"Advances":[0],"in":[1,9,26,44,64,147,162],"deep":[2,30,168,171],"reinforcement":[3,104],"learning":[4,146],"have":[5],"demonstrated":[6],"its":[7],"effectiveness":[8],"a":[10,34,86,96,108],"wide":[11],"variety":[12],"of":[13,20,36,39,55,112,139],"domains.":[14],"Deep":[15],"neural":[16,31],"networks":[17,32],"are":[18],"capable":[19],"approximating":[21],"value":[22],"functions":[23],"and":[24,102,126,165,176],"policies":[25],"complex":[27],"environments.":[28],"However,":[29],"inherit":[33],"number":[35],"drawbacks.":[37],"Lack":[38],"interpretability":[40],"limits":[41],"their":[42,69,76],"usability":[43],"many":[45,72],"safety-critical":[46],"real-world":[47,73],"scenarios.":[48],"Moreover,":[49],"they":[50],"rely":[51],"on":[52],"huge":[53],"amounts":[54,138],"data":[56,122],"to":[57,71,83,90,98,142],"learn":[58],"efficiently.":[59],"This":[60],"may":[61],"be":[62],"suitable":[63],"simulated":[65],"tasks,":[66],"but":[67],"restricts":[68],"use":[70],"applications.":[74],"Finally,":[75],"generalization":[77],"capability":[78],"is":[79,88],"low,":[80],"the":[81,113,145],"ability":[82],"determine":[84],"that":[85,120,133],"situation":[87],"similar":[89],"one":[91],"encountered":[92],"previously.":[93],"We":[94,106,131],"present":[95],"method":[97],"combine":[99],"external":[100],"knowledge":[101,125,141],"interpretable":[103],"learning.":[105],"derive":[107],"rule-based":[109],"variant":[110],"version":[111],"Sarsa(\u03bb)":[114],"algorithm,":[115],"which":[116],"we":[117],"call":[118],"Sarsa-rb(\u03bb),":[119],"augments":[121],"with":[123],"prior":[124,140],"exploits":[127],"similarities":[128],"among":[129],"states.":[130],"demonstrate":[132],"our":[134],"approach":[135],"leverages":[136],"small":[137],"significantly":[143],"accelerate":[144],"multiple":[148],"domains":[149],"such":[150],"as":[151],"trading":[152],"or":[153],"visual":[154],"navigation.":[155],"The":[156],"resulting":[157],"agent":[158],"provides":[159],"substantial":[160],"gains":[161],"training":[163],"speed":[164],"performance":[166],"over":[167,179],"q-learning":[169],"(DQN),":[170],"deterministic":[172],"policy":[173,181],"gradients":[174],"(DDPG),":[175],"improves":[177],"stability":[178],"proximal":[180],"optimization":[182],"(PPO).":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}