{"id":"https://openalex.org/W4408859658","doi":"https://doi.org/10.1109/tcyb.2025.3548821","title":"Balancing State Exploration and Skill Diversity in Unsupervised Skill Discovery","display_name":"Balancing State Exploration and Skill Diversity in Unsupervised Skill Discovery","publication_year":2025,"publication_date":"2025-03-26","ids":{"openalex":"https://openalex.org/W4408859658","doi":"https://doi.org/10.1109/tcyb.2025.3548821","pmid":"https://pubmed.ncbi.nlm.nih.gov/40138236"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2025.3548821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2025.3548821","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","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/A5115594797","display_name":"Xin Liu","orcid":"https://orcid.org/0000-0002-7857-3058"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7857-3058","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053853035","display_name":"Yaran Chen","orcid":"https://orcid.org/0000-0001-9356-0610"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaran Chen","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9356-0610","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guixing Chen","orcid":"https://orcid.org/0009-0003-3560-5667"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guixing Chen","raw_affiliation_strings":["Industry Incubation Center, Nanjing Institute of Software Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0003-3560-5667","affiliations":[{"raw_affiliation_string":"Industry Incubation Center, Nanjing Institute of Software Technology, Nanjing, China","institution_ids":["https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327745","display_name":"Haoran Li","orcid":"https://orcid.org/0000-0003-2559-9585"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Li","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2559-9585","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8218-9633","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.8388,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.96832738,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"55","issue":"5","first_page":"2234","last_page":"2247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13844","display_name":"Higher Education Learning Practices","score":0.925000011920929,"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":0.925000011920929,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9052000045776367,"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/diversity","display_name":"Diversity (politics)","score":0.5910134315490723},{"id":"https://openalex.org/keywords/discovery-learning","display_name":"Discovery learning","score":0.5381940007209778},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4663151204586029},{"id":"https://openalex.org/keywords/dreyfus-model-of-skill-acquisition","display_name":"Dreyfus model of skill acquisition","score":0.45691993832588196},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4322356581687927},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.39991486072540283},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.37530484795570374},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.35611748695373535},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.21448248624801636}],"concepts":[{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.5910134315490723},{"id":"https://openalex.org/C2779786715","wikidata":"https://www.wikidata.org/wiki/Q1393166","display_name":"Discovery learning","level":2,"score":0.5381940007209778},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4663151204586029},{"id":"https://openalex.org/C132758656","wikidata":"https://www.wikidata.org/wiki/Q5307365","display_name":"Dreyfus model of skill acquisition","level":2,"score":0.45691993832588196},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4322356581687927},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39991486072540283},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.37530484795570374},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.35611748695373535},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.21448248624801636},{"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2025.3548821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2025.3548821","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},{"id":"pmid:40138236","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40138236","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 cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1058100664","display_name":null,"funder_award_id":"104GJHZ2022013GC","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6219202550","display_name":null,"funder_award_id":"62293545","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G800914696","display_name":null,"funder_award_id":"62136008","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":47,"referenced_works":["https://openalex.org/W2076337359","https://openalex.org/W2089943482","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2966477753","https://openalex.org/W3038678879","https://openalex.org/W3207544809","https://openalex.org/W4252279978","https://openalex.org/W4294691690","https://openalex.org/W4360584370","https://openalex.org/W4388052875","https://openalex.org/W4391554393","https://openalex.org/W4395680426","https://openalex.org/W4396909851","https://openalex.org/W4400770903","https://openalex.org/W4408047562","https://openalex.org/W6682948231","https://openalex.org/W6684921986","https://openalex.org/W6730153900","https://openalex.org/W6747387971","https://openalex.org/W6748603076","https://openalex.org/W6756303580","https://openalex.org/W6762863188","https://openalex.org/W6764281707","https://openalex.org/W6764724164","https://openalex.org/W6765240361","https://openalex.org/W6773447848","https://openalex.org/W6778883912","https://openalex.org/W6780559895","https://openalex.org/W6782858274","https://openalex.org/W6791000347","https://openalex.org/W6791194670","https://openalex.org/W6796667233","https://openalex.org/W6798213610","https://openalex.org/W6799458897","https://openalex.org/W6803067813","https://openalex.org/W6810117360","https://openalex.org/W6811098490","https://openalex.org/W6849750003","https://openalex.org/W6852461623","https://openalex.org/W6852879801","https://openalex.org/W6857107556","https://openalex.org/W6857440262","https://openalex.org/W6857587328","https://openalex.org/W6858079367","https://openalex.org/W6868825112","https://openalex.org/W6929204088"],"related_works":["https://openalex.org/W2368973361","https://openalex.org/W2753770108","https://openalex.org/W4236583520","https://openalex.org/W2322261865","https://openalex.org/W4398861705","https://openalex.org/W2348296524","https://openalex.org/W2734736160","https://openalex.org/W2409468626","https://openalex.org/W4206863193","https://openalex.org/W2365199309"],"abstract_inverted_index":{"Unsupervised":[0],"skill":[1,33,43,63,96,129],"discovery":[2,34,64],"seeks":[3],"to":[4,23,37,54,88,104,124],"acquire":[5],"different":[6,109,152],"useful":[7],"skills":[8,20,49,72,174],"without":[9],"extrinsic":[10],"reward":[11,87,103],"via":[12],"unsupervised":[13,71],"reinforcement":[14],"learning":[15],"(RL),":[16],"with":[17],"the":[18,47,106,118,134,137,176],"discovered":[19,138],"efficiently":[21],"adapting":[22],"multiple":[24],"downstream":[25,164],"tasks":[26],"in":[27,175],"various":[28],"ways.":[29],"However,":[30],"recent":[31],"advanced":[32],"methods":[35],"struggle":[36],"well":[38],"balance":[39,125],"state":[40,126],"exploration":[41,86,127,173],"and":[42,52,69,98,128,142,171],"diversity,":[44,130],"particularly":[45],"when":[46],"potential":[48],"are":[50],"rich":[51],"hard":[53],"discern.":[55],"In":[56],"this":[57],"article,":[58],"we":[59],"propose":[60],"contrastive":[61,79,101],"dynamic":[62,80,114],"(ComSD)":[65],"which":[66,131],"generates":[67],"diverse":[68,149],"exploratory":[70,95,153],"through":[73],"a":[74,84,99,112],"novel":[75,100,113],"intrinsic":[76],"incentive,":[77],"named":[78],"reward.":[81],"It":[82,166],"contains":[83],"particle-based":[85],"make":[89],"agents":[90],"access":[91],"far-reaching":[92,172],"states":[93],"for":[94,155],"acquisition,":[97],"diversity":[102],"promote":[105],"discriminability":[107],"between":[108,117],"skills.":[110,139],"Moreover,":[111],"weighting":[115],"mechanism":[116],"above":[119],"two":[120],"rewards":[121],"is":[122],"proposed":[123],"further":[132],"enhances":[133],"quality":[135],"of":[136],"Extensive":[140],"experiments":[141],"analysis":[143],"demonstrate":[144],"that":[145],"ComSD":[146],"can":[147,167],"generate":[148],"behaviors":[150],"at":[151],"levels":[154],"multijoint":[156],"robots,":[157],"enabling":[158],"state-of-the-art":[159],"adaptation":[160],"performance":[161],"on":[162],"challenging":[163,177],"tasks.":[165],"also":[168],"discover":[169],"distinguishable":[170],"tree-like":[178],"2-D":[179],"maze.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
