{"id":"https://openalex.org/W3201094358","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533820","title":"Unsupervised Discovery of Transitional Skills for Deep Reinforcement Learning","display_name":"Unsupervised Discovery of Transitional Skills for Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3201094358","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533820","mag":"3201094358"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5008722982","display_name":"Qiangxing Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiangxing Tian","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","School of Engineering, Westlake University, Hangzhou, China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"School of Engineering, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386972","display_name":"Jinxin Liu","orcid":"https://orcid.org/0000-0001-7217-3611"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxin Liu","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","School of Engineering, Westlake University, Hangzhou, China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"School of Engineering, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086239439","display_name":"Guanchu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanchu Wang","raw_affiliation_strings":["Westlake University,School of Engineering,Hangzhou,China","School of Engineering, Westlake University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Westlake University,School of Engineering,Hangzhou,China","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"School of Engineering, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100665183","display_name":"Donglin Wang","orcid":"https://orcid.org/0000-0003-1359-6440"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donglin Wang","raw_affiliation_strings":["Westlake University,School of Engineering,Hangzhou,China","Westlake Institute for Advanced Study, Hangzhou, China","School of Engineering, Westlake University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Westlake University,School of Engineering,Hangzhou,China","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"Westlake Institute for Advanced Study, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"School of Engineering, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008722982"],"corresponding_institution_ids":["https://openalex.org/I3133055985","https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.84,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78967857,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9923999905586243,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.705351710319519},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6614382266998291},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6172420382499695},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5382930636405945},{"id":"https://openalex.org/keywords/transition","display_name":"Transition (genetics)","score":0.50319904088974},{"id":"https://openalex.org/keywords/skills-management","display_name":"Skills management","score":0.48388418555259705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4568305015563965},{"id":"https://openalex.org/keywords/communication-skills","display_name":"Communication skills","score":0.455888569355011},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13203850388526917},{"id":"https://openalex.org/keywords/pedagogy","display_name":"Pedagogy","score":0.08122777938842773},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07245057821273804},{"id":"https://openalex.org/keywords/medical-education","display_name":"Medical education","score":0.06978580355644226}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.705351710319519},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6614382266998291},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6172420382499695},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5382930636405945},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.50319904088974},{"id":"https://openalex.org/C97082442","wikidata":"https://www.wikidata.org/wiki/Q1934361","display_name":"Skills management","level":2,"score":0.48388418555259705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4568305015563965},{"id":"https://openalex.org/C2988115150","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication skills","level":2,"score":0.455888569355011},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13203850388526917},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.08122777938842773},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07245057821273804},{"id":"https://openalex.org/C509550671","wikidata":"https://www.wikidata.org/wiki/Q126945","display_name":"Medical education","level":1,"score":0.06978580355644226},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W115285041","https://openalex.org/W1522301498","https://openalex.org/W2000514530","https://openalex.org/W2078150668","https://openalex.org/W2139612737","https://openalex.org/W2144558232","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2164424353","https://openalex.org/W2170899200","https://openalex.org/W2188721763","https://openalex.org/W2556477470","https://openalex.org/W2606433045","https://openalex.org/W2735089625","https://openalex.org/W2781726626","https://openalex.org/W2788781499","https://openalex.org/W2803281228","https://openalex.org/W2909460318","https://openalex.org/W2920362155","https://openalex.org/W2922007426","https://openalex.org/W2950614095","https://openalex.org/W2951557330","https://openalex.org/W2954142106","https://openalex.org/W2962779270","https://openalex.org/W2962887844","https://openalex.org/W2963019567","https://openalex.org/W2963438456","https://openalex.org/W2964118020","https://openalex.org/W2964121744","https://openalex.org/W2964161785","https://openalex.org/W2964935470","https://openalex.org/W3014232838","https://openalex.org/W3034780381","https://openalex.org/W3035717769","https://openalex.org/W3122081773","https://openalex.org/W4288289109","https://openalex.org/W4289242739","https://openalex.org/W6604628494","https://openalex.org/W6631190155","https://openalex.org/W6662616117","https://openalex.org/W6682849425","https://openalex.org/W6741115023","https://openalex.org/W6756557100","https://openalex.org/W6760405395"],"related_works":["https://openalex.org/W2351598489","https://openalex.org/W1487158083","https://openalex.org/W2409596940","https://openalex.org/W2021041026","https://openalex.org/W4220995918","https://openalex.org/W1873016047","https://openalex.org/W1567497517","https://openalex.org/W3027219236","https://openalex.org/W4385895391","https://openalex.org/W2605693607"],"abstract_inverted_index":{"By":[0,77],"maximizing":[1],"an":[2,79],"information":[3,101],"theoretic":[4,102],"objective,":[5],"a":[6,32,60,99],"few":[7],"recent":[8],"methods":[9],"empower":[10],"the":[11,15,35,43,46,50,85,111,125,136,146],"agent":[12],"to":[13,30,39,49,66,72],"explore":[14],"environment":[16],"and":[17,94,119,122],"learn":[18,67],"skills":[19,29,69,96,118,134,141],"without":[20],"extrinsic":[21],"reward.":[22],"However,":[23],"when":[24],"considering":[25],"using":[26],"multiple":[27],"consecutive":[28],"complete":[31],"specific":[33],"task,":[34],"transition":[36,132],"from":[37],"one":[38],"another":[40],"cannot":[41],"guarantee":[42],"success":[44],"of":[45,127,133,139],"process":[47],"due":[48],"evident":[51],"gap":[52],"between":[53,87],"skills.":[54,76],"In":[55],"this":[56],"paper,":[57],"we":[58],"propose":[59],"novel":[61,100],"unsupervised":[62],"reinforcement":[63],"learning":[64,114],"approach":[65],"transitional":[68,95,120,140],"in":[70,130],"addition":[71],"pursuing":[73],"diverse":[74,116],"primitive":[75,93,117],"introducing":[78],"extra":[80],"latent":[81],"variable":[82],"for":[83],"exploring":[84],"dependence":[86],"skills,":[88,121],"our":[89,108,128],"method":[90,129],"discovers":[91],"both":[92,115],"by":[97],"optimizing":[98],"objective.":[103],"Considering":[104],"various":[105],"robotic":[106],"tasks,":[107],"results":[109],"demonstrate":[110],"effectiveness":[112],"on":[113,145],"further":[123],"exhibit":[124],"superiority":[126],"smooth":[131],"over":[135],"baselines.":[137],"Videos":[138],"can":[142],"be":[143],"found":[144],"project":[147],"website:":[148],"https://sites.google.com/view/udts-skill.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}
