{"id":"https://openalex.org/W7162812668","doi":"https://doi.org/10.5555/3635637.3663064","title":"Automatic Curriculum for Unsupervised Reinforcement Learning","display_name":"Automatic Curriculum for Unsupervised Reinforcement Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7162812668","doi":"https://doi.org/10.5555/3635637.3663064"},"language":"en","primary_location":{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/b292af19-f1be-4696-936e-a611a3c14b52","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/b292af19-f1be-4696-936e-a611a3c14b52","pdf_url":"https://pure.tue.nl/ws/files/391710408/p2002.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yang, Y, Zhou, T, Han, L, Fang, M & Pechenizkiy, M 2024, Automatic Curriculum for Unsupervised Reinforcement Learning. in Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent System, AAMAS-2024. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), pp. 2002-2010, 23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024, Auckland, New Zealand, 6/05/24. < https://www.ifaamas.org/Proceedings/aamas2024/ >","raw_type":"info:eu-repo/semantics/conferenceObject"},"type":"conference-paper","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.tue.nl/ws/files/391710408/p2002.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137344709","display_name":"Yucheng Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yucheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137393302","display_name":"Tianyi Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Tianyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137374839","display_name":"Lei Han","orcid":null},"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":"Han, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137344715","display_name":"Meng Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fang, Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133998039","display_name":"Mykola; id_orcid 0000-0003-4955-0743 Pechenizkiy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210088784","display_name":"ACT Foundation","ror":"https://ror.org/009qwqe18","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210088784"]},{"id":"https://openalex.org/I4210149743","display_name":"Sinai Health System","ror":"https://ror.org/05j8naw58","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210149743"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pechenizkiy, Mykola; id_orcid 0000-0003-4955-0743","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.2851000130176544,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.2851000130176544,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2587999999523163,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.03269999846816063,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7430999875068665},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5831999778747559},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4900999963283539},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.46939998865127563},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.43540000915527344},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.38530001044273376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8019999861717224},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7430999875068665},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6144000291824341},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5831999778747559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5807999968528748},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4900999963283539},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.38530001044273376},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2806999981403351},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2597000002861023}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/b292af19-f1be-4696-936e-a611a3c14b52","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/b292af19-f1be-4696-936e-a611a3c14b52","pdf_url":"https://pure.tue.nl/ws/files/391710408/p2002.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yang, Y, Zhou, T, Han, L, Fang, M & Pechenizkiy, M 2024, Automatic Curriculum for Unsupervised Reinforcement Learning. in Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent System, AAMAS-2024. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), pp. 2002-2010, 23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024, Auckland, New Zealand, 6/05/24. < https://www.ifaamas.org/Proceedings/aamas2024/ >","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/b292af19-f1be-4696-936e-a611a3c14b52","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/b292af19-f1be-4696-936e-a611a3c14b52","pdf_url":"https://pure.tue.nl/ws/files/391710408/p2002.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yang, Y, Zhou, T, Han, L, Fang, M & Pechenizkiy, M 2024, Automatic Curriculum for Unsupervised Reinforcement Learning. in Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent System, AAMAS-2024. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), pp. 2002-2010, 23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024, Auckland, New Zealand, 6/05/24. < https://www.ifaamas.org/Proceedings/aamas2024/ >","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.6249879598617554,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7162812668.pdf","grobid_xml":"https://content.openalex.org/works/W7162812668.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unsupervised":[0],"reinforcement":[1],"learning":[2,50,114],"(URL)":[3],"relies":[4],"on":[5,29,121,142],"carefully":[6],"designed":[7],"training":[8,44],"objectives":[9,111],"rather":[10],"than":[11],"task":[12],"rewards":[13],"to":[14,40,84,108,147],"learn":[15],"general":[16],"skills.":[17,56],"However,":[18],"we":[19,61,96],"lack":[20],"quantitative":[21],"evaluation":[22],"metrics":[23,67,80,144],"for":[24,33,112],"URL":[25,37,82,110,149],"but":[26],"mainly":[27],"rely":[28],"visualizations":[30],"of":[31,54,66,73,133],"trajectories":[32,88],"comparison.":[34],"Moreover,":[35],"most":[36],"methods":[38],"choose":[39],"optimize":[41],"a":[42,64,103,118],"single":[43],"objective,":[45],"which":[46],"may":[47],"hinder":[48],"later-stage":[49],"and":[51,87,92,139],"the":[52,123,131],"development":[53],"new":[55],"To":[57],"bridge":[58],"these":[59,79],"gaps,":[60],"first":[62],"introduce":[63],"combination":[65],"that":[68,77,101],"can":[69],"evaluate":[70],"diverse":[71],"properties":[72],"URL.":[74],"We":[75],"show":[76],"balancing":[78],"in":[81,117,127,136],"leads":[83],"better":[85],"performance":[86,141],"with":[89],"empirical":[90],"evidence":[91],"theoretical":[93],"insights.":[94],"Next,":[95],"develop":[97],"an":[98],"automatic":[99],"curriculum":[100],"uses":[102],"non-stationary":[104],"multi-armed":[105],"bandit":[106],"algorithm":[107],"select":[109],"different":[113,128],"episodes,":[115],"resulting":[116],"balanced":[119,140],"improvement":[120],"all":[122],"metrics.":[124],"Extensive":[125],"experiments":[126],"environments":[129],"demonstrate":[130],"advantages":[132],"our":[134],"method":[135],"achieving":[137],"promising":[138],"multiple":[143],"when":[145],"compared":[146],"recent":[148],"methods.":[150]},"counts_by_year":[],"updated_date":"2026-07-02T06:12:58.138171","created_date":"2026-05-30T00:00:00"}