{"id":"https://openalex.org/W4392642287","doi":"https://doi.org/10.1109/lra.2024.3375714","title":"Self-Supervised Curriculum Generation for Autonomous Reinforcement Learning Without Task-Specific Knowledge","display_name":"Self-Supervised Curriculum Generation for Autonomous Reinforcement Learning Without Task-Specific Knowledge","publication_year":2024,"publication_date":"2024-03-11","ids":{"openalex":"https://openalex.org/W4392642287","doi":"https://doi.org/10.1109/lra.2024.3375714"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3375714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3375714","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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 Robotics and Automation Letters","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/A5100444575","display_name":"Sang-Hyun Lee","orcid":"https://orcid.org/0009-0007-3360-4758"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sang-Hyun Lee","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0007-3360-4758","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048311228","display_name":"Seung\u2010Woo Seo","orcid":"https://orcid.org/0000-0003-4890-8563"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung-Woo Seo","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-4890-8563","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.3773,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50893097,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"9","issue":"5","first_page":"4043","last_page":"4050"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9995999932289124,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9933000206947327,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9718000292778015,"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/task","display_name":"Task (project management)","score":0.64903724193573},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6355834603309631},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.6190968751907349},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5505846738815308},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40891557931900024},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.3394603729248047},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32381972670555115},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.30908870697021484},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16862887144088745},{"id":"https://openalex.org/keywords/pedagogy","display_name":"Pedagogy","score":0.16540053486824036},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.06382665038108826}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.64903724193573},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6355834603309631},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.6190968751907349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5505846738815308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40891557931900024},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.3394603729248047},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32381972670555115},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.30908870697021484},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16862887144088745},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.16540053486824036},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.06382665038108826}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2024.3375714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3375714","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320336769","display_name":"Institute of Engineering Research, Seoul National University","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2155007355","https://openalex.org/W2529658650","https://openalex.org/W2962736495","https://openalex.org/W2963092423","https://openalex.org/W2968340082","https://openalex.org/W2990747716","https://openalex.org/W3016525976","https://openalex.org/W3040408533","https://openalex.org/W4226458162","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6746595151","https://openalex.org/W6747473740","https://openalex.org/W6756303580","https://openalex.org/W6767997047","https://openalex.org/W6768397756","https://openalex.org/W6771179988","https://openalex.org/W6776601253","https://openalex.org/W6785599724","https://openalex.org/W6802752636","https://openalex.org/W6803699115","https://openalex.org/W6811396868"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W3196817267"],"abstract_inverted_index":{"A":[0],"significant":[1],"bottleneck":[2],"in":[3,162],"applying":[4],"current":[5],"reinforcement":[6,46],"learning":[7,47,77,111],"algorithms":[8,49],"to":[9,15,35,108,121,124,183,186],"real-world":[10],"scenarios":[11],"is":[12,157],"the":[13,17,33,65,75,109,119,140,148,151,181],"need":[14],"reset":[16,23,56,90,123],"environment":[18],"between":[19],"every":[20],"episode.":[21],"This":[22],"process":[24],"demands":[25],"substantial":[26],"human":[27],"intervention,":[28],"making":[29],"it":[30],"difficult":[31],"for":[32,53],"agent":[34,120,149,182],"learn":[36],"continuously":[37],"and":[38,57,126,179,191],"autonomously.":[39],"Several":[40],"recent":[41],"works":[42],"have":[43],"introduced":[44],"autonomous":[45],"(ARL)":[48],"that":[50,102,138,170],"generate":[51,104,175],"curricula":[52,62],"jointly":[54],"training":[55],"forward":[58,152],"policies.":[59],"While":[60],"their":[61],"can":[63,103,174],"reduce":[64],"number":[66],"of":[67],"required":[68],"manual":[69,199],"resets":[70],"by":[71],"taking":[72],"into":[73],"account":[74],"agent's":[76,110],"progress,":[78],"they":[79],"rely":[80],"on":[81],"task-specific":[82,114],"knowledge,":[83],"such":[84],"as":[85],"predefined":[86],"initial":[87,128,145],"states":[88],"or":[89],"reward":[91],"functions.":[92],"In":[93],"this":[94],"paper,":[95],"we":[96,133],"propose":[97],"a":[98,105,135,163],"novel":[99],"ARL":[100,172],"algorithm":[101,173],"curriculum":[106,117,178],"adaptive":[107,177],"progress":[112],"without":[113],"knowledge.":[115],"Our":[116,166],"empowers":[118],"autonomously":[122],"diverse":[125],"informative":[127],"states.":[129],"To":[130],"achieve":[131],"this,":[132],"introduce":[134],"success":[136,141,155],"discriminator":[137,156],"estimates":[139],"probability":[142],"from":[143],"each":[144],"state":[146],"when":[147],"follows":[150],"policy.":[153],"The":[154],"trained":[158],"with":[159,196],"relabeled":[160],"transitions":[161],"self-supervised":[164],"manner.":[165],"experimental":[167],"results":[168],"demonstrate":[169],"our":[171],"an":[176],"enable":[180],"efficiently":[184],"bootstrap":[185],"solve":[187],"sparse-reward":[188],"maze":[189],"navigation":[190],"manipulation":[192],"tasks,":[193],"outperforming":[194],"baselines":[195],"significantly":[197],"fewer":[198],"resets.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}