{"id":"https://openalex.org/W4415178611","doi":"https://doi.org/10.1109/tnnls.2025.3613857","title":"Unsupervised Skill Discovery Through Skill Regions Differentiation","display_name":"Unsupervised Skill Discovery Through Skill Regions Differentiation","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W4415178611","doi":"https://doi.org/10.1109/tnnls.2025.3613857","pmid":"https://pubmed.ncbi.nlm.nih.gov/41086075"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3613857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3613857","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5101645983","display_name":"Ting Xiao","orcid":"https://orcid.org/0000-0003-1694-0294"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ting Xiao","raw_affiliation_strings":["Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, Shanghai, China","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058064944","display_name":"Jiakun Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiakun Zheng","raw_affiliation_strings":["East China University of Science and Technology, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113231897","display_name":"Rushuai Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Rushuai Yang","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Sai Kung, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Sai Kung, Hong Kong","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104307561","display_name":"Kang Xu","orcid":"https://orcid.org/0000-0001-6040-3002"},"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":"Kang Xu","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-6040-3002","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081325393","display_name":"Qiaosheng Zhang","orcid":"https://orcid.org/0000-0001-6114-8453"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiaosheng Zhang","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6114-8453","affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346747","display_name":"Peng Liu","orcid":"https://orcid.org/0000-0001-6568-1335"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Liu","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100621319","display_name":"Zhe Wang","orcid":"https://orcid.org/0000-0002-3759-2041"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Wang","raw_affiliation_strings":["Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3759-2041","affiliations":[{"raw_affiliation_string":"Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, Shanghai, China","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044788927","display_name":"Chenjia Bai","orcid":"https://orcid.org/0000-0002-8379-9385"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenjia Bai","raw_affiliation_strings":["China Telecom, Institute of Artificial Intelligence (TeleAI), Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8379-9385","affiliations":[{"raw_affiliation_string":"China Telecom, Institute of Artificial Intelligence (TeleAI), Shanghai, China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101645983"],"corresponding_institution_ids":["https://openalex.org/I1327237609"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30834611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"2","first_page":"907","last_page":"921"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13844","display_name":"Higher Education Learning Practices","score":0.9819999933242798,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13844","display_name":"Higher Education Learning Practices","score":0.9819999933242798,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14025","display_name":"Educational Technology and Assessment","score":0.9617000222206116,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/autoencoder","display_name":"Autoencoder","score":0.7828999757766724},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6166999936103821},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5098999738693237},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4677000045776367},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4648999869823456},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.42969998717308044},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.41040000319480896}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7828999757766724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6679999828338623},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6460000276565552},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6166999936103821},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5784000158309937},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5098999738693237},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4677000045776367},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4648999869823456},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C88482812","wikidata":"https://www.wikidata.org/wiki/Q6453666","display_name":"Modular programming","level":2,"score":0.39070001244544983},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C132758656","wikidata":"https://www.wikidata.org/wiki/Q5307365","display_name":"Dreyfus model of skill acquisition","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3613857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3613857","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:41086075","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41086075","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6503363755","display_name":null,"funder_award_id":"62306115","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7108700631","display_name":null,"funder_award_id":"62306242","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7870373927","display_name":null,"funder_award_id":"62476087","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1988526405","https://openalex.org/W2097931172","https://openalex.org/W2124352385","https://openalex.org/W2902907165","https://openalex.org/W2948978827","https://openalex.org/W2959895084","https://openalex.org/W2963523627","https://openalex.org/W3198659451","https://openalex.org/W4205430897","https://openalex.org/W4285278949","https://openalex.org/W4311415873","https://openalex.org/W4313156423","https://openalex.org/W4321611535","https://openalex.org/W4385462854","https://openalex.org/W4393160146","https://openalex.org/W4408859658"],"related_works":[],"abstract_inverted_index":{"Unsupervised":[0],"reinforcement":[1],"learning":[2,13],"(RL)":[3],"aims":[4],"to":[5,85,110],"discover":[6],"diverse":[7],"behaviors":[8],"that":[9,62,124],"can":[10],"accelerate":[11],"the":[12,64,67,74,86,121],"of":[14,66,70,77],"downstream":[15,155],"tasks.":[16,156],"Previous":[17],"methods":[18,40],"typically":[19],"focus":[20],"on":[21,120],"entropy-based":[22,29],"exploration":[23,30,127],"or":[24],"empowerment-driven":[25],"skill":[26,59,72,104],"learning.":[27],"However,":[28],"struggles":[31],"in":[32,48,106,128,136,153],"large-scale":[33],"state":[34,49,68,82,138],"spaces":[35],"(e.g.,":[36],"images),":[37],"and":[38,139,149],"empowerment-based":[39],"with":[41,99],"mutual":[42],"information":[43],"(MI)":[44],"estimations":[45],"have":[46],"limitations":[47],"exploration.":[50],"To":[51],"address":[52],"these":[53],"challenges,":[54],"we":[55,93,114,142],"propose":[56],"a":[57,95,129],"novel":[58,96],"discovery":[60],"objective":[61],"maximizes":[63],"deviation":[65],"density":[69],"one":[71],"from":[73],"explored":[75],"regions":[76],"other":[78],"skills,":[79],"encouraging":[80],"inter-skill":[81],"diversity":[83],"similar":[84],"initial":[87],"MI":[88],"objective.":[89],"For":[90],"state-density":[91],"estimation,":[92],"construct":[94],"conditional":[97],"autoencoder":[98,123],"soft":[100],"modularization":[101],"for":[102],"different":[103],"policies":[105],"high-dimensional":[107],"space.":[108,132],"Meanwhile,":[109],"incentivize":[111],"intra-skill":[112],"exploration,":[113],"formulate":[115],"an":[116],"intrinsic":[117],"reward":[118],"based":[119],"learned":[122],"resembles":[125],"count-based":[126],"compact":[130],"latent":[131],"Through":[133],"extensive":[134],"experiments":[135],"challenging":[137],"image-based":[140],"tasks,":[141],"find":[143],"our":[144],"method":[145],"learns":[146],"meaningful":[147],"skills":[148],"achieves":[150],"superior":[151],"performance":[152],"various":[154]},"counts_by_year":[],"updated_date":"2026-02-08T09:19:03.324500","created_date":"2025-10-15T00:00:00"}