{"id":"https://openalex.org/W4406983065","doi":"https://doi.org/10.1109/tits.2025.3532519","title":"Curricular Subgoals for Inverse Reinforcement Learning","display_name":"Curricular Subgoals for Inverse Reinforcement Learning","publication_year":2025,"publication_date":"2025-01-30","ids":{"openalex":"https://openalex.org/W4406983065","doi":"https://doi.org/10.1109/tits.2025.3532519"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2025.3532519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2025.3532519","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","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/A5090854835","display_name":"Shunyu Liu","orcid":"https://orcid.org/0000-0003-0584-9129"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shunyu Liu","raw_affiliation_strings":["State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0584-9129","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039449527","display_name":"Yunpeng Qing","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunpeng Qing","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7376-9847","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101093052","display_name":"Shuqi Xu","orcid":"https://orcid.org/0000-0002-7873-4456"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqi Xu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100677284","display_name":"Hongyan Wu","orcid":"https://orcid.org/0000-0002-8221-6766"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyan Wu","raw_affiliation_strings":["College of Software Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Software Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090918351","display_name":"Jiangtao Zhang","orcid":"https://orcid.org/0000-0002-5063-6854"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangtao Zhang","raw_affiliation_strings":["College of Software Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Software Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111146495","display_name":"Jingyuan Cong","orcid":"https://orcid.org/0000-0002-8974-4609"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyuan Cong","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101992061","display_name":"Tianhao Chen","orcid":"https://orcid.org/0000-0002-4454-1269"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhao Chen","raw_affiliation_strings":["College of Software Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Software Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007774284","display_name":"Yun-Fu Liu","orcid":"https://orcid.org/0000-0002-4390-6916"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun-Fu Liu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026532752","display_name":"Mingli Song","orcid":"https://orcid.org/0000-0003-2621-6048"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingli Song","raw_affiliation_strings":["State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2621-6048","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82131209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"26","issue":"3","first_page":"3016","last_page":"3027"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.7466999888420105,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.7466999888420105,"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/computer-science","display_name":"Computer science","score":0.6324677467346191},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.62482750415802},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44588813185691833},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4318457841873169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42938217520713806},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.24915382266044617},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.07477304339408875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6324677467346191},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.62482750415802},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44588813185691833},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4318457841873169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42938217520713806},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.24915382266044617},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.07477304339408875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2025.3532519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2025.3532519","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2655623952","display_name":null,"funder_award_id":"226-2024-00058","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6585374557","display_name":null,"funder_award_id":"LHZSD24F020001","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1540821927","https://openalex.org/W2051228319","https://openalex.org/W2057587543","https://openalex.org/W2139754237","https://openalex.org/W2296073425","https://openalex.org/W2963411833","https://openalex.org/W3034819467","https://openalex.org/W3049574859","https://openalex.org/W3090027660","https://openalex.org/W3122081773","https://openalex.org/W3146823280","https://openalex.org/W3175599258","https://openalex.org/W3189353415","https://openalex.org/W3191742182","https://openalex.org/W4224984798","https://openalex.org/W4306910464","https://openalex.org/W4309804352"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"Inverse":[0,91],"Reinforcement":[1,92],"Learning":[2,93],"(IRL)":[3],"aims":[4],"to":[5,13,40,67,105,122,158,180],"reconstruct":[6],"the":[7,42,46,49,59,68,75,116,132,166,174,181],"reward":[8,38,70,143,162],"function":[9],"from":[10],"expert":[11,120],"demonstrations":[12],"facilitate":[14],"policy":[15],"learning,":[16],"and":[17,48,62,72,168],"has":[18],"demonstrated":[19],"its":[20],"remarkable":[21],"success":[22],"in":[23,78],"imitation":[24],"learning.":[25],"To":[26,139],"promote":[27],"expert-like":[28],"behavior,":[29],"existing":[30],"IRL":[31],"methods":[32,176],"mainly":[33],"focus":[34],"on":[35,154,165],"learning":[36],"global":[37,53],"functions":[39,144],"minimize":[41],"trajectory":[43],"difference":[44],"between":[45],"imitator":[47],"expert.":[50],"However,":[51],"these":[52,155],"designs":[54],"are":[55],"still":[56],"limited":[57],"by":[58],"redundant":[60],"noise":[61],"error":[63],"propagation":[64],"problems,":[65],"leading":[66],"unsuitable":[69],"assignment":[71],"thus":[73],"downgrading":[74],"agent":[76,107,118],"capability":[77],"complex":[79],"multi-stage":[80],"tasks.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85,148],"propose":[86],"a":[87,150],"novel":[88],"Curricular":[89],"Subgoal-based":[90],"(CSIRL)":[94],"framework,":[95],"that":[96,173],"explicitly":[97],"disentangles":[98],"one":[99],"task":[100,137],"with":[101],"several":[102],"local":[103,142],"subgoals":[104,157],"guide":[106],"imitation.":[108],"Specifically,":[109],"CSIRL":[110],"firstly":[111],"introduces":[112],"decision":[113],"uncertainty":[114],"of":[115,135],"trained":[117],"over":[119],"trajectories":[121],"dynamically":[123],"select":[124],"specific":[125],"states":[126],"as":[127,184,186],"subgoals,":[128],"which":[129],"directly":[130],"determines":[131],"exploration":[133],"boundary":[134],"different":[136],"stages.":[138],"further":[140],"acquire":[141],"for":[145],"each":[146],"stage,":[147],"customize":[149],"meta-imitation":[151],"objective":[152],"based":[153],"curricular":[156],"train":[159],"an":[160],"intrinsic":[161],"generator.":[163],"Experiments":[164],"D4RL":[167],"autonomous":[169],"driving":[170],"benchmarks":[171],"demonstrate":[172],"proposed":[175],"yields":[177],"results":[178],"superior":[179],"state-of-the-art":[182],"counterparts,":[183],"well":[185],"better":[187],"interpretability.":[188],"Our":[189],"code":[190],"is":[191],"publicly":[192],"available":[193],"at":[194],"<uri":[195],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[196],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/Plankson/CSIRL</uri>.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}