{"id":"https://openalex.org/W2741594138","doi":"https://doi.org/10.24963/ijcai.2017/353","title":"Autonomous Task Sequencing for Customized Curriculum Design in Reinforcement Learning","display_name":"Autonomous Task Sequencing for Customized Curriculum Design in Reinforcement Learning","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2741594138","doi":"https://doi.org/10.24963/ijcai.2017/353","mag":"2741594138"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/353","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/353","pdf_url":"https://www.ijcai.org/proceedings/2017/0353.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0353.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032114961","display_name":"Sanmit Narvekar","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanmit Narvekar","raw_affiliation_strings":["University of Texas at Austin","Department of Computer Science, University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059212363","display_name":"Jivko Sinapov","orcid":"https://orcid.org/0000-0003-4852-026X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jivko Sinapov","raw_affiliation_strings":["University of Texas at Austin","Department of Computer Science, University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001594330","display_name":"Peter Stone","orcid":"https://orcid.org/0000-0002-6795-420X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Stone","raw_affiliation_strings":["University of Texas at Austin","Department of Computer Science, University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":5.2557,"has_fulltext":true,"cited_by_count":92,"citation_normalized_percentile":{"value":0.9693215,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2536","last_page":"2542"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.9959999918937683,"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"}},{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.7901811599731445},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.7627962827682495},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7087420225143433},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.660199761390686},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5592992305755615},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5077570676803589},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.49186038970947266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4655607044696808},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42728447914123535},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4259144067764282},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.42214539647102356},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.42155206203460693},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3241211175918579},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2668534517288208},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11241227388381958},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10719245672225952},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.06703782081604004}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7901811599731445},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.7627962827682495},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7087420225143433},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.660199761390686},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5592992305755615},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5077570676803589},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49186038970947266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4655607044696808},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42728447914123535},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4259144067764282},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42214539647102356},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.42155206203460693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3241211175918579},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2668534517288208},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11241227388381958},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10719245672225952},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.06703782081604004},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2017/353","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/353","pdf_url":"https://www.ijcai.org/proceedings/2017/0353.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/353","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/353","pdf_url":"https://www.ijcai.org/proceedings/2017/0353.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1482799704","display_name":null,"funder_award_id":"IIS-1651089","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G1718516081","display_name":null,"funder_award_id":"CNS-1330072","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G187671969","display_name":null,"funder_award_id":"IIS-1637736","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1886462947","display_name":null,"funder_award_id":"21C184-01","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G3614397566","display_name":null,"funder_award_id":"FA9550-14-1-0087","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4174258917","display_name":"II-NEW:  Infrastructure for a Building-Wide Intelligence","funder_award_id":"1305287","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5761287370","display_name":null,"funder_award_id":"CNS-1330072","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6008779683","display_name":null,"funder_award_id":"CNS-1330072","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G6050185415","display_name":null,"funder_award_id":"21C184-01","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G6098521345","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6991911153","display_name":"EAGER: Human-Aware Navigation in Populated Indoor Environments","funder_award_id":"1651089","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7187758091","display_name":null,"funder_award_id":"FA9550-14-1-0087","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G7548593011","display_name":null,"funder_award_id":"21C184-01","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7998559894","display_name":null,"funder_award_id":"CNS-1305287","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G8634898801","display_name":null,"funder_award_id":"FA9550-14-1-0087","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8653745736","display_name":"NRI: Robots that Learn to Communicate through Natural Human Dialog","funder_award_id":"1637736","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G869166546","display_name":null,"funder_award_id":"CNS-1305287","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8821898666","display_name":"CPS: Breakthrough: Reinforcement Learning Algorithms for Cyber-Physical Systems","funder_award_id":"1330072","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2741594138.pdf","grobid_xml":"https://content.openalex.org/works/W2741594138.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W36691172","https://openalex.org/W41554520","https://openalex.org/W158722652","https://openalex.org/W1492014007","https://openalex.org/W1510402218","https://openalex.org/W1546944959","https://openalex.org/W1995688924","https://openalex.org/W2004030284","https://openalex.org/W2056584142","https://openalex.org/W2097381042","https://openalex.org/W2106008664","https://openalex.org/W2121863487","https://openalex.org/W2126565096","https://openalex.org/W2129427976","https://openalex.org/W2133040789","https://openalex.org/W2141559023","https://openalex.org/W2169743339","https://openalex.org/W2271262891","https://openalex.org/W2476301537","https://openalex.org/W2578423033","https://openalex.org/W2581240229","https://openalex.org/W4214717370","https://openalex.org/W6629461247","https://openalex.org/W6755854181","https://openalex.org/W6892110240"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894"],"abstract_inverted_index":{"Transfer":[0],"learning":[1,17,28,166],"is":[2],"a":[3,12,19,45,50,89,92,111,171],"method":[4,112,154],"where":[5,38],"an":[6,104,115,118,126,147],"agent":[7,40,105,160],"reuses":[8],"knowledge":[9,43,102],"learned":[10],"in":[11,121,146],"source":[13],"task":[14],"to":[15,32,73,124,133,165],"improve":[16,162],"on":[18],"target":[20],"task.":[21],"Recent":[22],"work":[23],"has":[24],"shown":[25],"that":[26,113,152,161],"transfer":[27],"can":[29],"be":[30],"extended":[31],"the":[33,39,74,79,86,99],"idea":[34],"of":[35,47,67,78,88,101,117],"curriculum":[36,90],"learning,":[37],"incrementally":[41],"accumulates":[42],"over":[44],"sequence":[46,135],"tasks":[48,136],"(i.e.":[49],"curriculum).":[51],"In":[52,81],"most":[53],"existing":[54],"work,":[55],"such":[56],"curricula":[57,156],"have":[58],"been":[59],"constructed":[60],"manually.":[61],"Furthermore,":[62],"they":[63],"are":[64],"fixed":[65],"ahead":[66],"time,":[68],"and":[69,109,143,150],"do":[70],"not":[71],"adapt":[72],"progress":[75],"or":[76,169],"abilities":[77],"agent.":[80],"this":[82,122],"paper,":[83],"we":[84],"formulate":[85],"design":[87],"as":[91,103],"Markov":[93],"Decision":[94],"Process,":[95],"which":[96],"directly":[97],"models":[98],"accumulation":[100],"interacts":[106],"with":[107,140],"tasks,":[108],"propose":[110],"approximates":[114],"execution":[116],"optimal":[119],"policy":[120],"MDP":[123],"produce":[125],"agent-specific":[127],"curriculum.":[128,174],"We":[129],"use":[130],"our":[131,153],"approach":[132],"automatically":[134],"for":[137,158],"3":[138],"agents":[139],"varying":[141],"sensing":[142],"action":[144],"capabilities":[145],"experimental":[148],"domain,":[149],"show":[151],"produces":[155],"customized":[157],"each":[159],"performance":[163],"relative":[164],"from":[167],"scratch":[168],"using":[170],"different":[172],"agent's":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}