{"id":"https://openalex.org/W4408399546","doi":"https://doi.org/10.1109/tcds.2025.3551298","title":"AutoSkill: Hierarchical Open-Ended Skill Acquisition for Long-Horizon Manipulation Tasks via Language-Modulated Rewards","display_name":"AutoSkill: Hierarchical Open-Ended Skill Acquisition for Long-Horizon Manipulation Tasks via Language-Modulated Rewards","publication_year":2025,"publication_date":"2025-03-13","ids":{"openalex":"https://openalex.org/W4408399546","doi":"https://doi.org/10.1109/tcds.2025.3551298"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2025.3551298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3551298","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Transactions on Cognitive and Developmental Systems","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":null,"display_name":"Zhenyang Lin","orcid":"https://orcid.org/0000-0002-1361-4824"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenyang Lin","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1361-4824","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041934391","display_name":"Yurou Chen","orcid":"https://orcid.org/0000-0002-0022-7219"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yurou Chen","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0022-7219","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091931348","display_name":"Zhiyong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Liu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2148-1846","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04546412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"5","first_page":"1141","last_page":"1152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9552000164985657,"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/computer-science","display_name":"Computer science","score":0.83486008644104},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5495412349700928},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.5438597202301025},{"id":"https://openalex.org/keywords/dreyfus-model-of-skill-acquisition","display_name":"Dreyfus model of skill acquisition","score":0.4789317548274994},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.34173762798309326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32302194833755493},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11357226967811584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.83486008644104},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5495412349700928},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.5438597202301025},{"id":"https://openalex.org/C132758656","wikidata":"https://www.wikidata.org/wiki/Q5307365","display_name":"Dreyfus model of skill acquisition","level":2,"score":0.4789317548274994},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.34173762798309326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32302194833755493},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11357226967811584},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2025.3551298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3551298","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2066379939","https://openalex.org/W2158782408","https://openalex.org/W2256420211","https://openalex.org/W2966271811","https://openalex.org/W2970641574","https://openalex.org/W3150398929","https://openalex.org/W3204657926","https://openalex.org/W3205786327","https://openalex.org/W4205130889","https://openalex.org/W4286375451","https://openalex.org/W4308299830","https://openalex.org/W4320015882","https://openalex.org/W4383097638","https://openalex.org/W4386736782","https://openalex.org/W4388660746","https://openalex.org/W4389352652","https://openalex.org/W4390872260","https://openalex.org/W4401414844","https://openalex.org/W4402727730"],"related_works":["https://openalex.org/W4233159725","https://openalex.org/W2347391878","https://openalex.org/W2347250522","https://openalex.org/W4388749683","https://openalex.org/W2051033938","https://openalex.org/W2759633009","https://openalex.org/W2330249823","https://openalex.org/W2883321025","https://openalex.org/W2083682122","https://openalex.org/W3037132908"],"abstract_inverted_index":{"A":[0],"desirable":[1],"property":[2],"of":[3,109,130],"generalist":[4],"robots":[5],"is":[6],"the":[7,39,86,128,142],"ability":[8],"to":[9,41,51,65,89,92],"both":[10,175],"bootstrap":[11,67],"diverse":[12],"skills":[13,71],"and":[14,55,68,119,132,139,145,177],"solve":[15],"new":[16,70,95,120,160],"long-horizon":[17,43,96],"tasks":[18,97],"in":[19,72,152,174,192],"open-ended":[20,101],"environments":[21,179],"without":[22,104],"human":[23],"intervention.":[24],"Recent":[25],"advancements":[26],"have":[27],"shown":[28],"that":[29,84,126],"large":[30],"language":[31],"models":[32],"(LLMs)":[33],"encapsulate":[34],"vast-scale":[35],"semantic":[36],"knowledge":[37],"about":[38],"world":[40,57],"enable":[42],"robot":[44,88,129],"planning.":[45],"However,":[46],"they":[47],"are":[48],"typically":[49],"restricted":[50],"reasoning":[52],"high-level":[53],"instructions":[54,135],"lack":[56],"grounding,":[58],"which":[59],"makes":[60],"it":[61],"difficult":[62],"for":[63,136,196],"them":[64],"coordinately":[66],"acquire":[69],"unstructured":[73],"environments.":[74],"To":[75],"this":[76],"end,":[77],"we":[78],"propose":[79],"AutoSkill,":[80],"a":[81,147,155],"hierarchical":[82,190],"system":[83],"empowers":[85],"physical":[87],"automatically":[90],"learn":[91],"cope":[93],"with":[94,154,167],"by":[98,124],"growing":[99],"an":[100,114],"skill":[102,116,121,134,137,143,161,169],"library":[103],"hand-crafted":[105],"rewards.":[106],"AutoSkill":[107],"consists":[108],"two":[110],"key":[111],"components:":[112],"1)":[113],"in-context":[115],"chain":[117],"generation":[118],"bootstrapping":[122],"guided":[123],"LLMs":[125],"inform":[127],"discrete":[131],"interpretable":[133],"retrieval":[138],"augmentation":[140],"within":[141],"library;":[144],"2)":[146],"zero-shot":[148],"language-modulated":[149],"reward":[150],"scheme":[151],"conjunction":[153],"meta":[156],"prompter":[157],"facilitates":[158],"online":[159,194],"acquisition":[162],"via":[163],"expert-free":[164],"supervision":[165],"aligned":[166],"proposed":[168],"directives.":[170],"Extensive":[171],"experiments":[172],"conducted":[173],"simulated":[176],"realistic":[178],"demonstrate":[180],"AutoSkill's":[181],"superiority":[182],"over":[183],"other":[184],"LLM-based":[185],"planners":[186],"as":[187,189],"well":[188],"methods":[191],"expediting":[193],"learning":[195],"novel":[197],"manipulation":[198],"tasks.":[199]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
