{"id":"https://openalex.org/W4310336120","doi":"https://doi.org/10.1109/tpami.2022.3223872","title":"Curriculum-Based Asymmetric Multi-Task Reinforcement Learning","display_name":"Curriculum-Based Asymmetric Multi-Task Reinforcement Learning","publication_year":2022,"publication_date":"2022-11-24","ids":{"openalex":"https://openalex.org/W4310336120","doi":"https://doi.org/10.1109/tpami.2022.3223872","pmid":"https://pubmed.ncbi.nlm.nih.gov/36417748"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3223872","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3223872","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/A5025364768","display_name":"Hanchi Huang","orcid":"https://orcid.org/0000-0001-5500-3311"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Hanchi Huang","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073681676","display_name":"Deheng Ye","orcid":"https://orcid.org/0000-0002-1754-1837"},"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":"Deheng Ye","raw_affiliation_strings":["Tencent Inc., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent Inc., Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042802004","display_name":"Li Shen","orcid":"https://orcid.org/0000-0001-5659-3464"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":["JD.com Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD.com Inc., Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100431792","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-3865-8145"},"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":"Wei Liu","raw_affiliation_strings":["Tencent Inc., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent Inc., Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025364768"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":2.7601,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.91685208,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"45","issue":"6","first_page":"7258","last_page":"7269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9648000001907349,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9624000191688538,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6815011501312256},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6805500388145447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6364100575447083},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6000458002090454},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48167169094085693},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.42931628227233887},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.4233616590499878},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17386838793754578},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14425981044769287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6815011501312256},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6805500388145447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6364100575447083},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6000458002090454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48167169094085693},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.42931628227233887},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.4233616590499878},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17386838793754578},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14425981044769287},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2022.3223872","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3223872","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:36417748","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36417748","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1517383877","https://openalex.org/W1924762813","https://openalex.org/W2076095618","https://openalex.org/W2097451239","https://openalex.org/W2140180727","https://openalex.org/W2150468603","https://openalex.org/W2151834591","https://openalex.org/W2152166054","https://openalex.org/W2296073425","https://openalex.org/W2460087882","https://openalex.org/W2964262254","https://openalex.org/W2978894944","https://openalex.org/W2996896271","https://openalex.org/W3040707741","https://openalex.org/W3141797743","https://openalex.org/W3164612304","https://openalex.org/W3210940825","https://openalex.org/W4231341614","https://openalex.org/W4293846201","https://openalex.org/W4295332890","https://openalex.org/W4297810554","https://openalex.org/W4366455181","https://openalex.org/W6630916141","https://openalex.org/W6682433143","https://openalex.org/W6683195989","https://openalex.org/W6718818137","https://openalex.org/W6719384148","https://openalex.org/W6738279954","https://openalex.org/W6739868092","https://openalex.org/W6740879895","https://openalex.org/W6742108279","https://openalex.org/W6743660412","https://openalex.org/W6745190604","https://openalex.org/W6745995898","https://openalex.org/W6747473740","https://openalex.org/W6748638692","https://openalex.org/W6757505405","https://openalex.org/W6769596995","https://openalex.org/W6771876938","https://openalex.org/W6775647304","https://openalex.org/W6781884759","https://openalex.org/W6785308759","https://openalex.org/W6785535465","https://openalex.org/W6796223860"],"related_works":["https://openalex.org/W1564680838","https://openalex.org/W2003125260","https://openalex.org/W2060591604","https://openalex.org/W2166791242","https://openalex.org/W3012440055","https://openalex.org/W2585162246","https://openalex.org/W2034202275","https://openalex.org/W1934413089","https://openalex.org/W1992291644","https://openalex.org/W2098419343"],"abstract_inverted_index":{"We":[0,139],"introduce":[1],"CAMRL,":[2],"the":[3,22,27,53,56,60,67,91,97,111,121,126,133,165,170],"first":[4],"curriculum-based":[5,32],"asymmetric":[6,44],"multi-task":[7,45,150],"learning":[8,16],"(AMTL)":[9],"algorithm":[10,174],"for":[11],"dealing":[12],"with":[13,84],"multiple":[14,85],"reinforcement":[15],"(RL)":[17],"tasks":[18],"altogether.":[19],"To":[20,65],"mitigate":[21],"negative":[23,75],"influence":[24],"of":[25,104,113,147,167],"customizing":[26],"one-off":[28],"training":[29,37,54,128],"order":[30],"in":[31,77,149],"AMTL,":[33,78],"CAMRL":[34,124,168],"switches":[35],"its":[36],"mode":[38],"between":[39],"parallel":[40],"single-task":[41,172],"RL":[42,46,173],"and":[43,59,72,89,96,130,136,161,175],"(MTRL),":[47],"according":[48],"to":[49,73,109,163],"an":[50],"indicator":[51],"regarding":[52],"time,":[55],"overall":[57],"performance,":[58],"performance":[61],"gap":[62],"among":[63],"tasks.":[64],"leverage":[66],"multi-sourced":[68],"prior":[69],"knowledge":[70],"flexibly":[71],"reduce":[74],"transfer":[76,134],"we":[79],"customize":[80],"a":[81,144],"composite":[82,122],"loss":[83,92],"differentiable":[86],"ranking":[87],"functions":[88],"optimize":[90],"through":[93],"alternating":[94],"optimization":[95],"Frank-Wolfe":[98],"algorithm.":[99],"The":[100,179],"uncertainty-based":[101],"automatic":[102],"adjustment":[103],"hyper-parameters":[105],"is":[106,181],"also":[107],"applied":[108],"eliminate":[110],"need":[112],"laborious":[114],"hyper-parameter":[115],"analysis":[116],"during":[117],"optimization.":[118],"By":[119],"optimizing":[120],"loss,":[123],"predicts":[125],"next":[127],"task":[129],"continuously":[131],"revisits":[132],"matrix":[135],"network":[137],"weights.":[138],"have":[140],"conducted":[141],"experiments":[142],"on":[143],"wide":[145],"range":[146],"benchmarks":[148],"RL,":[151],"covering":[152],"Gym-minigrid,":[153],"Meta-world,":[154],"Atari":[155],"video":[156],"games,":[157],"vision-based":[158],"PyBullet":[159],"tasks,":[160],"RLBench,":[162],"show":[164],"improvements":[166],"over":[169],"corresponding":[171],"state-of-the-art":[176],"MTRL":[177],"algorithms.":[178],"code":[180],"available":[182],"at:":[183],"https://github.com/huanghanchi/CAMRL.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2025-10-10T00:00:00"}