{"id":"https://openalex.org/W4408913866","doi":"https://doi.org/10.1109/tase.2025.3554861","title":"Auxiliary Reward Generation With Transition Distance Representation Learning","display_name":"Auxiliary Reward Generation With Transition Distance Representation Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408913866","doi":"https://doi.org/10.1109/tase.2025.3554861"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2025.3554861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3554861","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","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/A5001645652","display_name":"Siyuan Li","orcid":"https://orcid.org/0000-0001-7965-598X"},"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":true,"raw_author_name":"Siyuan Li","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102082987","display_name":"Shijie Han","orcid":"https://orcid.org/0000-0003-4780-3815"},"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":"Shijie Han","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101304618","display_name":"Yingnan Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingnan Zhao","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Engineering University, Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqin Yang","raw_affiliation_strings":["Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institute of Automation, Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"institute of Automation, Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014109600","display_name":"Qianchuan Zhao","orcid":"https://orcid.org/0000-0002-7952-5621"},"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":"Qianchuan Zhao","raw_affiliation_strings":["Institute of Systems Engineering, Tsinghua University, Beijing, China","Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Systems Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"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":["Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001645652"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":11.0301,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.97580851,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"22","issue":null,"first_page":"13728","last_page":"13740"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11365","display_name":"Islamic Finance and Banking Studies","score":0.8525999784469604,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11365","display_name":"Islamic Finance and Banking Studies","score":0.8525999784469604,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.7907999753952026,"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/T11644","display_name":"Spam and Phishing Detection","score":0.7767999768257141,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/representation","display_name":"Representation (politics)","score":0.491832971572876},{"id":"https://openalex.org/keywords/transition","display_name":"Transition (genetics)","score":0.4900999963283539},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4591694474220276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3977698087692261}],"concepts":[{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.491832971572876},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.4900999963283539},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4591694474220276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3977698087692261},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2025.3554861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3554861","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5658153603","display_name":null,"funder_award_id":"No.62306088","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7136179577","display_name":null,"funder_award_id":"YQ2024007","funder_id":"https://openalex.org/F4320323085","funder_display_name":"Natural Science Foundation of Heilongjiang Province"},{"id":"https://openalex.org/G915215520","display_name":null,"funder_award_id":"62306088","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/F4320323085","display_name":"Natural Science Foundation of Heilongjiang Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1497992513","https://openalex.org/W1957496711","https://openalex.org/W1968962398","https://openalex.org/W2096733369","https://openalex.org/W2154997814","https://openalex.org/W2157364932","https://openalex.org/W2296073425","https://openalex.org/W2567705466","https://openalex.org/W2788455270","https://openalex.org/W2842511635","https://openalex.org/W2886885155","https://openalex.org/W3040707741","https://openalex.org/W3048804154","https://openalex.org/W3159243351","https://openalex.org/W4213019189","https://openalex.org/W4252279978","https://openalex.org/W4283788634","https://openalex.org/W4311415873","https://openalex.org/W4396941373","https://openalex.org/W6623316541","https://openalex.org/W6638088447","https://openalex.org/W6676557315","https://openalex.org/W6677884823","https://openalex.org/W6683195989","https://openalex.org/W6721408278","https://openalex.org/W6741002519","https://openalex.org/W6756256016","https://openalex.org/W6759301632","https://openalex.org/W6762573206","https://openalex.org/W6763704811","https://openalex.org/W6765407481","https://openalex.org/W6767317771","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6782766965","https://openalex.org/W6785204124","https://openalex.org/W6790486821","https://openalex.org/W6810111970","https://openalex.org/W6810343060","https://openalex.org/W6838968391","https://openalex.org/W6848588639","https://openalex.org/W6849548236","https://openalex.org/W6852461623","https://openalex.org/W6853863622","https://openalex.org/W6857151620"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,20,60,135,169,244,278],"(RL)":[2],"has":[3],"shown":[4,199],"strengths":[5],"in":[6,14,130,137,188,200,225],"challenging":[7],"sequential":[8],"decision-making":[9],"problems.":[10],"The":[11,148],"reward":[12,53,78,258,299],"function":[13],"RL":[15],"is":[16,43],"crucial":[17],"to":[18,45,194,205,320],"the":[19,25,33,65,88,98,103,108,114,118,122,127,152,156,160,180,185,195,213,242,274,283,293,305],"performance,":[21],"as":[22,198],"it":[23],"quantifies":[24],"degree":[26],"of":[27,141,154],"task":[28],"completion.":[29],"In":[30,121],"real-world":[31],"problems,":[32],"rewards":[34,101,110,187],"are":[35],"predominantly":[36],"human-designed,":[37],"which":[38,166,280],"requires":[39],"laborious":[40],"tuning,":[41],"and":[42,84,133,146,159,171,223,228,246,264],"susceptible":[44],"human":[46,91,269],"cognitive":[47],"biases.":[48],"To":[49,240],"achieve":[50],"automatic":[51],"auxiliary":[52,77,100,164,186,257],"generation,":[54],"we":[55,74,94,125,177,254,311],"propose":[56],"a":[57,138,189,216,296,314],"novel":[58,276],"representation":[59,277],"approach":[61,129],"that":[62,97,179,218],"can":[63,191,281],"measure":[64,282],"\u201ctransition":[66,284],"distance\u201d":[67,285],"between":[68,286],"states.":[69,287],"Building":[70],"upon":[71],"these":[72,252],"representations,":[73],"introduce":[75,255],"an":[76,256],"generation":[79,259],"technique":[80,217,260,272],"for":[81,90,208,215,250,261],"both":[82,131,226,262],"single-task":[83,227,263],"skill-chaining":[85,229,265],"scenarios":[86,266],"without":[87,267],"need":[89,214],"knowledge.":[92],"Furthermore,":[93],"theoretically":[95],"show":[96],"proposed":[99,128,275],"maintain":[102],"policy":[104,115,183,243,248,290,306],"invariance":[105],"property,":[106],"i.e.,":[107],"generated":[109],"will":[111],"not":[112],"hurt":[113],"optimality":[116],"under":[117],"original":[119],"rewards.":[120],"experiment":[123,149],"section,":[124],"evaluate":[126],"online":[132],"offline":[134],"settings":[136],"wide":[139],"range":[140],"tasks,":[142,253],"including":[143],"robot":[144,220,236,294,318],"manipulation":[145,182,238,323],"locomotion.":[147],"results":[150],"demonstrate":[151,178],"effectiveness":[153],"measuring":[155],"transition":[157],"distance":[158],"induced":[161],"improvement":[162],"by":[163,301,308],"rewards,":[165],"promotes":[167],"better":[168],"efficiency":[170,222],"increases":[172],"convergent":[173],"stability.":[174],"Beyond":[175],"that,":[176],"learned":[181],"with":[184],"simulator":[190],"be":[192],"transferred":[193],"real":[196,315],"robot,":[197],"<uri":[201],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[202],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://sites.google.com/view/transition-distance-rp/tdrp</uri>.":[203],"Note":[204],"Practitioners\u2014The":[206],"motivation":[207],"this":[209],"paper":[210],"arises":[211],"from":[212],"enhances":[219],"skill-learning":[221],"performance":[224,249],"scenarios.":[230],"Our":[231],"research":[232],"primarily":[233],"focuses":[234],"on":[235],"arm":[237,319],"tasks.":[239,324],"accelerate":[241],"process":[245],"improve":[247],"executing":[251],"requiring":[268],"expertise.":[270],"This":[271],"leverages":[273],"approach,":[279],"During":[288],"each":[289],"training":[291],"round,":[292],"receives":[295],"dense":[297],"reshaped":[298],"created":[300],"our":[302,309],"approach.":[303],"Using":[304],"trained":[307],"method,":[310],"successfully":[312],"control":[313],"Franka":[316],"Panda":[317],"complete":[321],"various":[322]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
