{"id":"https://openalex.org/W3175186743","doi":"https://doi.org/10.1109/lra.2021.3091885","title":"Learning to Discover Task-Relevant Features for Interpretable Reinforcement Learning","display_name":"Learning to Discover Task-Relevant Features for Interpretable Reinforcement Learning","publication_year":2021,"publication_date":"2021-07-21","ids":{"openalex":"https://openalex.org/W3175186743","doi":"https://doi.org/10.1109/lra.2021.3091885","mag":"3175186743"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2021.3091885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3091885","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Robotics and Automation Letters","raw_type":"journal-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/A5100739520","display_name":"Qiyuan Zhang","orcid":"https://orcid.org/0000-0002-8519-4259"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiyuan Zhang","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027912723","display_name":"Xiaoteng Ma","orcid":"https://orcid.org/0000-0002-7250-6268"},"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":"Xiaoteng Ma","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046252455","display_name":"Yiqin Yang","orcid":"https://orcid.org/0000-0002-8748-1964"},"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":"Yiqin Yang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8748-1964","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100756591","display_name":"Chenghao Li","orcid":"https://orcid.org/0000-0001-6882-3511"},"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":"Chenghao Li","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101912623","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0002-9386-5825"},"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":"Jun Yang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9386-5825","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345672","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0001-9107-6390"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0001-9107-6390","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100644630","display_name":"Bin Liang","orcid":"https://orcid.org/0000-0002-8591-8843"},"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":"Bin Liang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8591-8843","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6997,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.76047109,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"6","issue":"4","first_page":"6601","last_page":"6607"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9976000189781189,"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":0.9975000023841858,"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":0.9000281095504761},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8717673420906067},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8159172534942627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6757040023803711},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6427804827690125},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6261625289916992},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5646949410438538},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5539940595626831},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5188023447990417},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.5048983693122864},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4884135127067566},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4678319990634918},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06685960292816162}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9000281095504761},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8717673420906067},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8159172534942627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6757040023803711},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6427804827690125},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6261625289916992},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5646949410438538},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5539940595626831},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5188023447990417},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.5048983693122864},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4884135127067566},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4678319990634918},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06685960292816162},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2021.3091885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3091885","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G6796436614","display_name":null,"funder_award_id":"61903215","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W218059538","https://openalex.org/W1924770834","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2727840223","https://openalex.org/W2765615734","https://openalex.org/W2781726626","https://openalex.org/W2799151646","https://openalex.org/W2842511635","https://openalex.org/W2900152462","https://openalex.org/W2908064123","https://openalex.org/W2962954781","https://openalex.org/W2963403868","https://openalex.org/W2970909667","https://openalex.org/W2980433389","https://openalex.org/W2994849131","https://openalex.org/W2995773109","https://openalex.org/W2996037775","https://openalex.org/W3035435378","https://openalex.org/W3036185205","https://openalex.org/W3101283005","https://openalex.org/W3125947392","https://openalex.org/W4288294128","https://openalex.org/W4289294484","https://openalex.org/W4295598622","https://openalex.org/W4295720520","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6608502305","https://openalex.org/W6640212811","https://openalex.org/W6739901393","https://openalex.org/W6744991969","https://openalex.org/W6747473740","https://openalex.org/W6749304979","https://openalex.org/W6750186571","https://openalex.org/W6756256016","https://openalex.org/W6757184387","https://openalex.org/W6763704883","https://openalex.org/W6765407481","https://openalex.org/W6768810269","https://openalex.org/W6771810092","https://openalex.org/W6772005887","https://openalex.org/W6779827379","https://openalex.org/W6780559895","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W4385957992","https://openalex.org/W4229079080","https://openalex.org/W4206534706","https://openalex.org/W4385965371","https://openalex.org/W4386025632","https://openalex.org/W2558685994","https://openalex.org/W3006943036","https://openalex.org/W4320854072","https://openalex.org/W4381383350","https://openalex.org/W3094337650"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"agents":[3],"are":[4,49],"often":[5],"fed":[6],"with":[7,100],"large-dimensional":[8],"observations":[9],"to":[10,32,44],"achieve":[11],"the":[12,19,55,95,106,120],"ideal":[13],"performance":[14,99],"in":[15],"complex":[16],"environments.":[17],"Unfortunately,":[18],"massive":[20],"observation":[21],"space":[22],"usually":[23],"contains":[24],"useless":[25],"or":[26],"even":[27],"adverse":[28],"features,":[29],"which":[30,48],"leads":[31],"low":[33],"sample":[34],"efficiency.":[35],"Existing":[36],"methods":[37,102],"rely":[38],"on":[39,88],"domain":[40,84],"knowledge":[41],"and":[42,90],"cross-validation":[43],"discover":[45],"efficient":[46],"features":[47,81,109],"informative":[50],"for":[51,110],"decision-making.":[52],"To":[53],"minimize":[54],"impact":[56],"of":[57,78,122],"prior":[58],"knowledge,":[59],"we":[60],"propose":[61],"a":[62,70,117],"temporal-adaptive":[63],"feature":[64],"attention":[65,72],"algorithm":[66],"(TAFA).":[67],"We":[68,112],"adopt":[69],"non-linear":[71],"module,":[73],"automatically":[74],"choosing":[75],"task-relevant":[76,108],"components":[77],"hand-crafted":[79],"state":[80],"without":[82],"any":[83],"knowledge.":[85],"Our":[86,124],"experiments":[87],"MuJoCo":[89],"TORCS":[91],"tasks":[92],"show":[93],"that":[94],"agent":[96],"achieves":[97],"competitive":[98],"state-of-the-art":[101],"while":[103],"successfully":[104],"identifying":[105],"most":[107],"free.":[111],"believe":[113],"our":[114],"work":[115],"takes":[116],"step":[118],"towards":[119],"interpretability":[121],"RL.":[123],"code":[125],"is":[126],"available":[127],"at":[128],"https://github.com/QiyuanZhang19/Temporal-Adaptive-Feature-Attention/tree/master.":[129]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}