{"id":"https://openalex.org/W4403059085","doi":"https://doi.org/10.1109/tcds.2024.3471645","title":"PDRL: Towards Deeper States and Further Behaviors in Unsupervised Skill Discovery by Progressive Diversity","display_name":"PDRL: Towards Deeper States and Further Behaviors in Unsupervised Skill Discovery by Progressive Diversity","publication_year":2024,"publication_date":"2024-10-02","ids":{"openalex":"https://openalex.org/W4403059085","doi":"https://doi.org/10.1109/tcds.2024.3471645"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2024.3471645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2024.3471645","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":"https://openalex.org/A5100613787","display_name":"Ziming He","orcid":"https://orcid.org/0009-0003-2218-8550"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziming He","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0009-0003-2218-8550","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chao Song","orcid":"https://orcid.org/0000-0001-8378-1209"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Song","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0001-8378-1209","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037024339","display_name":"Jingchen Li","orcid":"https://orcid.org/0000-0003-0905-0816"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingchen Li","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-0905-0816","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013665827","display_name":"Haobin Shi","orcid":"https://orcid.org/0000-0003-2180-8941"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haobin Shi","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-2180-8941","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100613787"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":1.492,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87103997,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"17","issue":"3","first_page":"495","last_page":"509"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14025","display_name":"Educational Technology and Assessment","score":0.9757000207901001,"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"}},"topics":[{"id":"https://openalex.org/T14025","display_name":"Educational Technology and Assessment","score":0.9757000207901001,"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"}},{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9276999831199646,"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":0.7312546372413635},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.7201322317123413},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4604542553424835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3474884629249573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7312546372413635},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.7201322317123413},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4604542553424835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3474884629249573},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2024.3471645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2024.3471645","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":[{"id":"https://openalex.org/G1586735782","display_name":null,"funder_award_id":"62476225","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3123168170","display_name":null,"funder_award_id":"2023YFF0905604","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8274292341","display_name":null,"funder_award_id":"62076202","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1786044565","https://openalex.org/W2791797404","https://openalex.org/W2963608065","https://openalex.org/W2992712483","https://openalex.org/W3100366369","https://openalex.org/W3168892396","https://openalex.org/W3171623979","https://openalex.org/W3216283008","https://openalex.org/W4225304231","https://openalex.org/W4285060105","https://openalex.org/W4285165559","https://openalex.org/W4384789618","https://openalex.org/W4387682202","https://openalex.org/W4388081402","https://openalex.org/W4393159608","https://openalex.org/W4395007752","https://openalex.org/W4397026139","https://openalex.org/W6604628494","https://openalex.org/W6677939520","https://openalex.org/W6730153900","https://openalex.org/W6737937804","https://openalex.org/W6740801417","https://openalex.org/W6747473740","https://openalex.org/W6748599296","https://openalex.org/W6748603076","https://openalex.org/W6752216738","https://openalex.org/W6753756885","https://openalex.org/W6762533131","https://openalex.org/W6764724164","https://openalex.org/W6768000218","https://openalex.org/W6773447848","https://openalex.org/W6778594666","https://openalex.org/W6785599724","https://openalex.org/W6793841834","https://openalex.org/W6797416203","https://openalex.org/W6797805403","https://openalex.org/W6802451544","https://openalex.org/W6803067813","https://openalex.org/W6811219444","https://openalex.org/W6838308872","https://openalex.org/W6849169497"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"We":[0],"present":[1],"progressive":[2],"diversity":[3,48,104],"reinforcement":[4,9,152],"learning":[5,10,19,62,153],"(PDRL),":[6],"an":[7],"unsupervised":[8],"(URL)":[11],"method":[12],"for":[13,60],"discovering":[14],"diverse":[15],"skills.":[16,96],"PDRL":[17,56,111,133,147],"encourages":[18],"behaviors":[20],"that":[21,30,132],"span":[22],"multiple":[23,129],"steps,":[24],"particularly":[25],"by":[26,84],"introducing":[27],"\u201cdeeper":[28],"states\u201d\u2014states":[29],"require":[31],"a":[32,117,135],"longer":[33],"sequence":[34],"of":[35,45,119,138],"actions":[36],"to":[37,63,76,91,141],"reach":[38],"without":[39,105],"repetition.":[40],"To":[41],"address":[42],"the":[43],"challenges":[44],"weak":[46,50],"skill":[47,61,67,103,125],"and":[49,66,72,93,102,121],"exploration":[51,65,101],"in":[52,150,158],"partially":[53],"observable":[54],"environments,":[55],"employs":[57],"two":[58],"indications":[59],"foster":[64],"diversity,":[68],"emphasizing":[69],"each":[70],"observation":[71],"subtrajectory's":[73],"accuracy":[74],"compared":[75,140],"its":[77],"predecessor.":[78],"Skill":[79],"latent":[80],"variables":[81],"are":[82],"represented":[83],"mappings":[85],"from":[86],"states":[87],"or":[88,108],"trajectories,":[89],"helping":[90],"distinguish":[92],"recover":[94],"learned":[95],"This":[97],"dual":[98],"representation":[99],"promotes":[100],"additional":[106],"modeling":[107],"prior":[109],"knowledge.":[110],"also":[112],"integrates":[113],"intrinsic":[114],"rewards":[115],"through":[116],"combination":[118],"observations":[120],"subtrajectories,":[122],"effectively":[123],"preventing":[124],"duplication.":[126],"Experiments":[127],"across":[128],"benchmarks":[130],"show":[131],"discovers":[134],"broader":[136],"range":[137],"skills":[139],"existing":[142],"methods.":[143],"Additionally,":[144],"pretraining":[145],"with":[146],"accelerates":[148],"fine-tuning":[149],"goal-conditioned":[151],"(GCRL)":[154],"tasks,":[155],"as":[156],"demonstrated":[157],"Fetch":[159],"robotic":[160],"manipulation":[161],"tasks.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}