{"id":"https://openalex.org/W4414359773","doi":"https://doi.org/10.24963/ijcai.2025/538","title":"Variational Offline Multi-agent Skill Discovery","display_name":"Variational Offline Multi-agent Skill Discovery","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359773","doi":"https://doi.org/10.24963/ijcai.2025/538"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/538","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/538","pdf_url":"https://www.ijcai.org/proceedings/2025/0538.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2025/0538.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100380049","display_name":"Jiayu Chen","orcid":"https://orcid.org/0000-0002-7708-5247"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayu Chen","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018464968","display_name":"Tian Lan","orcid":"https://orcid.org/0000-0003-3010-8090"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian Lan","raw_affiliation_strings":["George Washington University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064822688","display_name":"Vaneet Aggarwal","orcid":"https://orcid.org/0000-0001-9131-4723"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vaneet Aggarwal","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30396893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4833","last_page":"4841"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14025","display_name":"Educational Technology and Assessment","score":0.9782999753952026,"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":0.9782999753952026,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.972000002861023,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9602000117301941,"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/codebase","display_name":"Codebase","score":0.7132999897003174},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6714000105857849},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5299000144004822},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.47870001196861267},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.33809998631477356},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.32910001277923584},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.3156000077724457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7811999917030334},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.7132999897003174},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6714000105857849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6201000213623047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5932000279426575},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5299000144004822},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47870001196861267},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33809998631477356},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.3156000077724457},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/538","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/538","pdf_url":"https://www.ijcai.org/proceedings/2025/0538.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2025/538","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/538","pdf_url":"https://www.ijcai.org/proceedings/2025/0538.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414359773.pdf","grobid_xml":"https://content.openalex.org/works/W4414359773.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Skills":[0],"are":[1],"effective":[2],"temporal":[3],"abstractions":[4,63],"established":[5],"for":[6,15,35],"sequential":[7],"decision":[8],"making,":[9],"which":[10,68],"enable":[11],"efficient":[12],"hierarchical":[13,134],"learning":[14,21,137,150],"long-horizon":[16],"tasks":[17,119,126],"and":[18,55,61,64,109,157],"facilitate":[19],"multi-task":[20,107],"through":[22],"their":[23],"transferability.":[24],"Despite":[25],"extensive":[26],"research,":[27],"research":[28],"gaps":[29],"remain":[30],"in":[31,41,96,152],"multi-agent":[32,43,66,135],"scenarios,":[33],"particularly":[34],"automatically":[36,88],"extracting":[37],"subgroup":[38,112],"coordination":[39],"patterns":[40],"a":[42,82,97],"task.":[44,98],"In":[45],"this":[46],"case,":[47],"we":[48],"propose":[49],"two":[50],"novel":[51],"auto-encoder":[52],"schemes:":[53],"VO-MASD-3D":[54],"VO-MASD-Hier,":[56],"to":[57,105],"simultaneously":[58],"capture":[59],"subgroup-":[60],"temporal-level":[62],"form":[65],"skills,":[67],"firstly":[69],"solves":[70],"the":[71,110,149],"aforementioned":[72],"challenge.":[73],"An":[74],"essential":[75],"algorithm":[76],"component":[77],"of":[78],"these":[79],"schemes":[80],"is":[81,163],"dynamic":[83],"grouping":[84],"function":[85],"that":[86,128],"can":[87,102,114,146],"detect":[89],"latent":[90],"subgroups":[91],"based":[92],"on":[93,124],"agent":[94],"interactions":[95],"Further,":[99],"our":[100,129,144],"method":[101,145],"be":[103,115],"applied":[104],"offline":[106],"data,":[108],"discovered":[111,142],"skills":[113,141],"transferred":[116],"across":[117],"relevant":[118],"without":[120],"retraining.":[121],"Empirical":[122],"evaluations":[123],"StarCraft":[125],"indicate":[127],"approach":[130],"significantly":[131],"outperforms":[132],"existing":[133],"reinforcement":[136],"(MARL)":[138],"methods.":[139],"Moreover,":[140],"using":[143],"effectively":[147],"reduce":[148],"difficulty":[151],"MARL":[153],"scenarios":[154],"with":[155],"delayed":[156],"sparse":[158],"reward":[159],"signals.":[160],"The":[161],"codebase":[162],"available":[164],"at:":[165],"https://github.com/LucasCJYSDL/VOMASD.":[166]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}