{"id":"https://openalex.org/W3098338892","doi":"https://doi.org/10.1109/tpami.2020.3037898","title":"Self-Supervised Discovering of Interpretable Features for Reinforcement Learning","display_name":"Self-Supervised Discovering of Interpretable Features for Reinforcement Learning","publication_year":2020,"publication_date":"2020-11-13","ids":{"openalex":"https://openalex.org/W3098338892","doi":"https://doi.org/10.1109/tpami.2020.3037898","mag":"3098338892","pmid":"https://pubmed.ncbi.nlm.nih.gov/33186101"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2020.3037898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2020.3037898","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5055957441","display_name":"Wenjie Shi","orcid":"https://orcid.org/0000-0001-8677-0011"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Shi","raw_affiliation_strings":["Department of Automation, Tsinghua University, 12442 Beijing, Beijing, China, (e-mail: shiwj16@mails.tsinghua.edu.cn)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, 12442 Beijing, Beijing, China, (e-mail: shiwj16@mails.tsinghua.edu.cn)","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013240918","display_name":"Gao Huang","orcid":"https://orcid.org/0000-0002-7251-0988"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao Huang","raw_affiliation_strings":["Department of Automation, Tsinghua University, 12442 Beijing, Beijing, China, (e-mail: gaohuang@tsinghua.edu.cn)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, 12442 Beijing, Beijing, China, (e-mail: gaohuang@tsinghua.edu.cn)","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068624597","display_name":"Shiji Song","orcid":"https://orcid.org/0000-0001-7361-9283"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiji Song","raw_affiliation_strings":["Department of Automation, Tsinghua University, 12442 Beijing, Beijing, China, (e-mail: shijis@tsinghua.edu.cn)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, 12442 Beijing, Beijing, China, (e-mail: shijis@tsinghua.edu.cn)","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101633421","display_name":"Zhuoyuan Wang","orcid":"https://orcid.org/0000-0002-1360-6218"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoyuan Wang","raw_affiliation_strings":["Department of Automation, Tsinghua University, 12442 Beijing, Beijing, China, (e-mail: zhuoyuan16@mails.tsinghua.edu.cn)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, 12442 Beijing, Beijing, China, (e-mail: zhuoyuan16@mails.tsinghua.edu.cn)","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102779964","display_name":"Tingyu Lin","orcid":"https://orcid.org/0009-0008-9825-686X"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingyu Lin","raw_affiliation_strings":["State Key Laboratory of Intelligent Manufacturing System Technology, Beijing, Beijing, China, (e-mail: lintingyu2003@sina.com)","[State Key Laboratory of Intelligent Manufacturing System Technology, Beijing, Beijing, China, (e-mail: lintingyu2003@sina.com)]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Manufacturing System Technology, Beijing, Beijing, China, (e-mail: lintingyu2003@sina.com)","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"[State Key Laboratory of Intelligent Manufacturing System Technology, Beijing, Beijing, China, (e-mail: lintingyu2003@sina.com)]","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100752413","display_name":"Cheng Wu","orcid":"https://orcid.org/0000-0002-8611-2665"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Wu","raw_affiliation_strings":["Department of Automatoion, Tsinghua University, 12442 Beijing, Beijing, China, (e-mail: wuc@tsinghua.edu.cn)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automatoion, Tsinghua University, 12442 Beijing, Beijing, China, (e-mail: wuc@tsinghua.edu.cn)","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.979,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.92933151,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"44","issue":"5","first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9961000084877014,"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":0.9890999794006348,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7629546523094177},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6572433114051819},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5619330406188965},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5421136617660522},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44748952984809875}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7629546523094177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6572433114051819},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5619330406188965},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5421136617660522},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44748952984809875}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2020.3037898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2020.3037898","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:33186101","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33186101","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4055798484","display_name":null,"funder_award_id":"61936009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4154278399","display_name":null,"funder_award_id":"2018YFB1702903","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5069583762","display_name":null,"funder_award_id":"2018AAA0100701","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G5872187165","display_name":null,"funder_award_id":"2018YFB1702903","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G6879802318","display_name":null,"funder_award_id":"61906106","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8753403390","display_name":null,"funder_award_id":"62022048","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":110,"referenced_works":["https://openalex.org/W112327418","https://openalex.org/W1178556121","https://openalex.org/W1562353621","https://openalex.org/W1849277567","https://openalex.org/W1901129140","https://openalex.org/W2060300932","https://openalex.org/W2120779958","https://openalex.org/W2133950705","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2155968351","https://openalex.org/W2173564293","https://openalex.org/W2187089797","https://openalex.org/W2195446438","https://openalex.org/W2257979135","https://openalex.org/W2259424905","https://openalex.org/W2270696664","https://openalex.org/W2282821441","https://openalex.org/W2336525064","https://openalex.org/W2346578521","https://openalex.org/W2487898712","https://openalex.org/W2559597482","https://openalex.org/W2563705555","https://openalex.org/W2564920024","https://openalex.org/W2567015638","https://openalex.org/W2590082389","https://openalex.org/W2594336441","https://openalex.org/W2605409611","https://openalex.org/W2606462007","https://openalex.org/W2626639386","https://openalex.org/W2630837129","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2776207810","https://openalex.org/W2781726626","https://openalex.org/W2805623918","https://openalex.org/W2809136100","https://openalex.org/W2891383942","https://openalex.org/W2907217398","https://openalex.org/W2907361867","https://openalex.org/W2910843367","https://openalex.org/W2921888626","https://openalex.org/W2924181074","https://openalex.org/W2925486737","https://openalex.org/W2945022240","https://openalex.org/W2954804306","https://openalex.org/W2962702317","https://openalex.org/W2962711930","https://openalex.org/W2962772482","https://openalex.org/W2962847771","https://openalex.org/W2962851944","https://openalex.org/W2962858109","https://openalex.org/W2962862931","https://openalex.org/W2962954781","https://openalex.org/W2963081790","https://openalex.org/W2963454359","https://openalex.org/W2963715038","https://openalex.org/W2963749936","https://openalex.org/W2963864421","https://openalex.org/W2963923407","https://openalex.org/W2964231903","https://openalex.org/W2965046886","https://openalex.org/W2965140792","https://openalex.org/W2965361505","https://openalex.org/W2970909667","https://openalex.org/W2970981858","https://openalex.org/W2976187852","https://openalex.org/W2988157455","https://openalex.org/W2990810232","https://openalex.org/W2997423597","https://openalex.org/W2998004401","https://openalex.org/W2999458807","https://openalex.org/W3004058922","https://openalex.org/W3012229961","https://openalex.org/W3012550998","https://openalex.org/W3037207827","https://openalex.org/W3100388886","https://openalex.org/W3101609372","https://openalex.org/W3103780890","https://openalex.org/W4288289200","https://openalex.org/W4293861706","https://openalex.org/W6604521175","https://openalex.org/W6684921986","https://openalex.org/W6685133223","https://openalex.org/W6685444567","https://openalex.org/W6687590523","https://openalex.org/W6694177581","https://openalex.org/W6731192180","https://openalex.org/W6731334075","https://openalex.org/W6733905848","https://openalex.org/W6734023089","https://openalex.org/W6736518430","https://openalex.org/W6737947904","https://openalex.org/W6738549535","https://openalex.org/W6739575509","https://openalex.org/W6739696289","https://openalex.org/W6741002519","https://openalex.org/W6744991969","https://openalex.org/W6746042458","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6751437432","https://openalex.org/W6752170072","https://openalex.org/W6757551904","https://openalex.org/W6760867800","https://openalex.org/W6763704883","https://openalex.org/W6765734322","https://openalex.org/W6767703609","https://openalex.org/W6780559895","https://openalex.org/W7027579263"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W2033914206"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,205],"(RL)":[3],"has":[4],"recently":[5],"led":[6],"to":[7,43,70,88,154,187],"many":[8],"breakthroughs":[9],"on":[10,111,199],"a":[11,61,81,122,192],"range":[12],"of":[13,28,33,74,168],"complex":[14],"control":[15],"tasks.":[16],"However,":[17],"the":[18,31,53,102,139,145,164,185],"agent's":[19,54,103],"decision-making":[20,166],"process":[21,167],"is":[22,86,121],"generally":[23],"not":[24,176],"transparent.":[25],"The":[26,128],"lack":[27],"interpretability":[29],"hinders":[30],"applicability":[32],"RL":[34,75],"in":[35],"safety-critical":[36],"scenarios.":[37],"While":[38],"several":[39,112],"methods":[40],"have":[41],"attempted":[42],"interpret":[44],"vision-based":[45,169],"RL,":[46],"most":[47,99],"come":[48],"without":[49],"detailed":[50],"explanation":[51],"for":[52,78,93,101,202],"behavior.":[55],"In":[56,171],"this":[57],"paper,":[58],"we":[59],"propose":[60],"self-supervised":[62,82,193,208],"interpretable":[63,68,83],"framework,":[64],"which":[65,97,120,195],"can":[66],"discover":[67],"features":[69],"enable":[71],"easy":[72],"understanding":[73],"agents":[76],"even":[77],"non-experts.":[79],"Specifically,":[80],"network":[84],"(SSINet)":[85],"employed":[87],"produce":[89],"fine-grained":[90],"attention":[91],"masks":[92],"highlighting":[94],"task-relevant":[95],"information,":[96],"constitutes":[98],"evidence":[100],"decisions.":[104],"We":[105],"verify":[106],"and":[107,143,182,210],"evaluate":[108],"our":[109,132,158,173],"method":[110,133,159,174],"Atari":[113],"2600":[114],"games":[115],"as":[116,118,207],"well":[117,148],"Duckietown,":[119],"challenging":[123],"self-driving":[124],"car":[125],"simulator":[126],"environment.":[127],"results":[129],"show":[130],"that":[131],"renders":[134],"empirical":[135],"evidences":[136],"about":[137],"how":[138],"agent":[140,146],"makes":[141],"decisions":[142],"why":[144],"performs":[147],"or":[149],"badly,":[150],"especially":[151],"when":[152],"transferred":[153],"novel":[155],"scenes.":[156],"Overall,":[157],"provides":[160],"valuable":[161],"insight":[162],"into":[163],"internal":[165],"RL.":[170],"addition,":[172],"does":[175],"use":[177],"any":[178],"external":[179],"labelled":[180],"data,":[181],"thus":[183],"demonstrates":[184],"possibility":[186],"learn":[188],"high-quality":[189],"mask":[190],"through":[191],"manner,":[194],"may":[196],"shed":[197],"light":[198],"new":[200],"paradigms":[201],"label-free":[203],"vision":[204],"such":[206],"segmentation":[209],"detection.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}