{"id":"https://openalex.org/W3197854638","doi":"https://doi.org/10.1109/tcyb.2021.3107202","title":"Addressing Hindsight Bias in Multigoal Reinforcement Learning","display_name":"Addressing Hindsight Bias in Multigoal Reinforcement Learning","publication_year":2021,"publication_date":"2021-09-08","ids":{"openalex":"https://openalex.org/W3197854638","doi":"https://doi.org/10.1109/tcyb.2021.3107202","mag":"3197854638","pmid":"https://pubmed.ncbi.nlm.nih.gov/34495860"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2021.3107202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2021.3107202","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Transactions on Cybernetics","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/A5044788927","display_name":"Chenjia Bai","orcid":"https://orcid.org/0000-0002-8379-9385"},"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"]},{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenjia Bai","raw_affiliation_strings":["Academy for Engineering & Technology, Fudan University, Shanghai, China","Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-8379-9385","affiliations":[{"raw_affiliation_string":"Academy for Engineering & Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100779971","display_name":"Lingxiao Wang","orcid":"https://orcid.org/0000-0002-1654-4681"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lingxiao Wang","raw_affiliation_strings":["Departments of Industrial Engineering and Management Sciences, Northwestern University, Evanston, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-1654-4681","affiliations":[{"raw_affiliation_string":"Departments of Industrial Engineering and Management Sciences, Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101934111","display_name":"Zhaoran Wang","orcid":"https://orcid.org/0000-0002-6617-4842"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yixin Wang","raw_affiliation_strings":["Department of EECS, University of California at Berkeley, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6617-4842","affiliations":[{"raw_affiliation_string":"Department of EECS, University of California at Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101934111","display_name":"Zhaoran Wang","orcid":"https://orcid.org/0000-0002-6617-4842"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaoran Wang","raw_affiliation_strings":["Departments of Industrial Engineering and Management Sciences, Northwestern University, Evanston, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departments of Industrial Engineering and Management Sciences, Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101414593","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0002-5147-2695"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhao","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, Tencent, China"],"raw_orcid":"https://orcid.org/0000-0002-5147-2695","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035413140","display_name":"Chenyao Bai","orcid":"https://orcid.org/0000-0003-3510-390X"},"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"]},{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyao Bai","raw_affiliation_strings":["Academy for Engineering & Technology, Fudan University, Shanghai, China","Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0003-3510-390X","affiliations":[{"raw_affiliation_string":"Academy for Engineering & Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100346747","display_name":"Peng Liu","orcid":"https://orcid.org/0000-0001-6568-1335"},"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":"Peng Liu","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0001-6568-1335","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5607,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.85995325,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"53","issue":"1","first_page":"392","last_page":"405"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9783999919891357,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.9992588758468628},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8583078384399414},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5858545303344727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5447817444801331},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4905087351799011},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4138903021812439},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.31332701444625854},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.26573699712753296}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.9992588758468628},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8583078384399414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5858545303344727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5447817444801331},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4905087351799011},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4138903021812439},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.31332701444625854},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26573699712753296},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2021.3107202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2021.3107202","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Transactions on Cybernetics","raw_type":"journal-article"},{"id":"pmid:34495860","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34495860","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 cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6812708429","display_name":"\u706b\u661f\u65cb\u7ffc\u98de\u884c\u5668\u8bbe\u8ba1\u7406\u8bba\u4e0e\u63a7\u5236\u6280\u672f\u7814\u7a76","funder_award_id":"51935005","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1503398984","https://openalex.org/W1964534398","https://openalex.org/W1965381771","https://openalex.org/W1980648727","https://openalex.org/W2034806082","https://openalex.org/W2109910161","https://openalex.org/W2143891888","https://openalex.org/W2145339207","https://openalex.org/W2150291618","https://openalex.org/W2761873684","https://openalex.org/W2766447205","https://openalex.org/W2890965997","https://openalex.org/W2902907165","https://openalex.org/W2908261578","https://openalex.org/W2909711564","https://openalex.org/W2915977493","https://openalex.org/W2948175577","https://openalex.org/W2962736495","https://openalex.org/W2967474307","https://openalex.org/W2986925736","https://openalex.org/W2990747716","https://openalex.org/W2998069546","https://openalex.org/W3026486560","https://openalex.org/W3034963685","https://openalex.org/W3036054814","https://openalex.org/W3092202606","https://openalex.org/W3093655779","https://openalex.org/W3098389716","https://openalex.org/W3128011616","https://openalex.org/W3130292943","https://openalex.org/W4206566734","https://openalex.org/W4214717370","https://openalex.org/W4233471163","https://openalex.org/W4292070111","https://openalex.org/W4293872189","https://openalex.org/W4297808394","https://openalex.org/W4310895557","https://openalex.org/W6616173779","https://openalex.org/W6635701881","https://openalex.org/W6638088447","https://openalex.org/W6640963894","https://openalex.org/W6679365036","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6735789912","https://openalex.org/W6740801417","https://openalex.org/W6745747580","https://openalex.org/W6748839928","https://openalex.org/W6753060773","https://openalex.org/W6754475338","https://openalex.org/W6754689381","https://openalex.org/W6758182352","https://openalex.org/W6758315252","https://openalex.org/W6759871227","https://openalex.org/W6760405395","https://openalex.org/W6762640273","https://openalex.org/W6762868464","https://openalex.org/W6763356705","https://openalex.org/W6765008394","https://openalex.org/W6766413688","https://openalex.org/W6767047803","https://openalex.org/W6767334564","https://openalex.org/W6767649332","https://openalex.org/W6771418060","https://openalex.org/W6779827379","https://openalex.org/W6781732661","https://openalex.org/W6795425552","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W3197854638","https://openalex.org/W3140454661","https://openalex.org/W4245029315","https://openalex.org/W1492315459","https://openalex.org/W1512434910","https://openalex.org/W2540910169","https://openalex.org/W3148904318","https://openalex.org/W2139970489","https://openalex.org/W2022803902","https://openalex.org/W2592762265"],"abstract_inverted_index":{"Multigoal":[0],"reinforcement":[1],"learning":[2,96],"(RL)":[3],"extends":[4],"the":[5,20,34,39,53,59,62,73,103,115,124],"typical":[6],"RL":[7,17,138],"with":[8],"goal-conditional":[9],"value":[10],"functions":[11],"and":[12,65,91,113],"policies.":[13],"One":[14],"efficient":[15,120],"multigoal":[16,99,137],"algorithm":[18,121],"is":[19,51,71],"hindsight":[21,28,54,85,104,111,125],"experience":[22],"replay":[23],"(HER).":[24],"By":[25],"treating":[26],"a":[27,46,89,94],"goal":[29],"from":[30],"failed":[31],"experiences":[32],"as":[33],"original":[35],"goal,":[36],"HER":[37,50,117],"enables":[38],"agent":[40],"to":[41,76,107],"receive":[42],"rewards":[43],"frequently.":[44],"However,":[45],"key":[47],"assumption":[48],"of":[49,61,110],"that":[52,83,122,132],"goals":[55,86,112],"do":[56],"not":[57,72],"change":[58],"likelihood":[60,90],"sampled":[63],"transitions":[64],"trajectories":[66],"used":[67],"in":[68,93,127,140],"training,":[69],"which":[70],"fact":[74],"according":[75],"our":[77],"analysis.":[78],"More":[79],"specifically,":[80],"we":[81],"show":[82,131],"using":[84],"changes":[87],"such":[88],"results":[92],"biased":[95],"objective":[97],"for":[98],"RL.":[100],"We":[101,129],"analyze":[102],"bias":[105,126],"due":[106],"this":[108],"use":[109],"propose":[114],"bias-corrected":[116],"(BHER),":[118],"an":[119],"corrects":[123],"training.":[128],"further":[130],"BHER":[133],"outperforms":[134],"several":[135],"state-of-the-art":[136],"approaches":[139],"challenging":[141],"robotics":[142],"tasks.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}