{"id":"https://openalex.org/W4251408821","doi":"https://doi.org/10.24963/ijcai.2017/757","title":"Curriculum Learning in Reinforcement Learning","display_name":"Curriculum Learning in Reinforcement Learning","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W4251408821","doi":"https://doi.org/10.24963/ijcai.2017/757"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/757","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/757","pdf_url":"https://www.ijcai.org/proceedings/2017/0757.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/2017/0757.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":true,"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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5032114961"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":1.2448,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.85604922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5195","last_page":"5196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9973999857902527,"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":0.9839000105857849,"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":0.7955090999603271},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7456903457641602},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6248145699501038},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5980120897293091},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.5623252987861633},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5127947926521301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43471765518188477},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.43280819058418274},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.42758485674858093},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09831079840660095},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.07097333669662476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7955090999603271},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7456903457641602},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6248145699501038},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5980120897293091},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.5623252987861633},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5127947926521301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43471765518188477},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43280819058418274},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.42758485674858093},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09831079840660095},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.07097333669662476},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"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/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2017/757","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/757","pdf_url":"https://www.ijcai.org/proceedings/2017/0757.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.2017/757","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/757","pdf_url":"https://www.ijcai.org/proceedings/2017/0757.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":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4","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/F4320310620","display_name":"University of Texas at Austin","ror":"https://ror.org/00hj54h04"},{"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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4251408821.pdf","grobid_xml":"https://content.openalex.org/works/W4251408821.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W36691172","https://openalex.org/W158722652","https://openalex.org/W2004030284","https://openalex.org/W2056584142","https://openalex.org/W2097381042","https://openalex.org/W2129427976","https://openalex.org/W2476301537","https://openalex.org/W2741594138"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W4220829754","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W2171010636"],"abstract_inverted_index":{"Transfer":[0],"learning":[1,4,17,40,66],"in":[2],"reinforcement":[3],"is":[5,47,68],"an":[6,56,86],"area":[7],"of":[8,18,38,52,91],"research":[9],"that":[10,62],"seeks":[11],"to":[12,41,48,58,85],"speed":[13,67],"up":[14],"or":[15,28,65],"improve":[16],"a":[19,50,92,101],"complex":[20],"target":[21,93],"task,":[22],"by":[23],"leveraging":[24],"knowledge":[25],"from":[26],"one":[27],"more":[29],"source":[30,53,82],"tasks.":[31],"This":[32],"thesis":[33],"will":[34],"extend":[35],"the":[36,45,89],"concept":[37],"transfer":[39],"curriculum":[42],"learning,":[43],"where":[44],"goal":[46],"design":[49],"sequence":[51],"tasks":[54,83,99],"for":[55,79,108],"agent":[57,87],"train":[59],"on,":[60],"such":[61,98],"final":[63],"performance":[64],"improved.":[69],"We":[70],"discuss":[71],"completed":[72],"work":[73],"on":[74],"this":[75],"topic,":[76],"including":[77],"methods":[78],"semi-automatically":[80],"generating":[81],"tailored":[84],"and":[88,95],"characteristics":[90],"domain,":[94],"automatically":[96],"sequencing":[97],"into":[100],"curriculum.":[102],"Finally,":[103],"we":[104],"also":[105],"present":[106],"ideas":[107],"future":[109],"work.":[110]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}