{"id":"https://openalex.org/W4412445030","doi":"https://doi.org/10.1109/lra.2025.3588784","title":"Multi-Task Multi-Agent Reinforcement Learning via Skill Graphs","display_name":"Multi-Task Multi-Agent Reinforcement Learning via Skill Graphs","publication_year":2025,"publication_date":"2025-07-15","ids":{"openalex":"https://openalex.org/W4412445030","doi":"https://doi.org/10.1109/lra.2025.3588784"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3588784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3588784","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5089159183","display_name":"Guobin Zhu","orcid":"https://orcid.org/0009-0002-2643-5304"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guobin Zhu","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-2643-5304","affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017969899","display_name":"Rui Zhou","orcid":"https://orcid.org/0000-0002-8572-1952"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhou","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049044867","display_name":"Wenkang Ji","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":"Wenkang Ji","raw_affiliation_strings":["WINDY Lab, Department of Artificial Intelligence, Westlake University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WINDY Lab, Department of Artificial Intelligence, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongyin Zhang","orcid":"https://orcid.org/0000-0002-9216-8403"},"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":"Hongyin Zhang","raw_affiliation_strings":["MiLAB Lab, Department of Artificial Intelligence, Westlake University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9216-8403","affiliations":[{"raw_affiliation_string":"MiLAB Lab, Department of Artificial Intelligence, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","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":["MiLAB Lab, Department of Artificial Intelligence, Westlake University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1359-6440","affiliations":[{"raw_affiliation_string":"MiLAB Lab, Department of Artificial Intelligence, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052346042","display_name":"Shiyu Zhao","orcid":"https://orcid.org/0000-0003-3098-8059"},"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":"Shiyu Zhao","raw_affiliation_strings":["WINDY Lab, Department of Artificial Intelligence, Westlake University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3098-8059","affiliations":[{"raw_affiliation_string":"WINDY Lab, Department of Artificial Intelligence, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5089159183"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":5.514,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95579721,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"10","issue":"9","first_page":"8650","last_page":"8657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8677999973297119,"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":0.8677999973297119,"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/task","display_name":"Task (project management)","score":0.7009681463241577},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.664779007434845},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.528251588344574},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4673585891723633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3812706470489502},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2770625054836273},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.11091500520706177},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08843761682510376}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7009681463241577},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.664779007434845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.528251588344574},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4673585891723633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3812706470489502},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2770625054836273},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.11091500520706177},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08843761682510376},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3588784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3588784","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4494429742","display_name":null,"funder_award_id":"62473320","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G716867869","display_name":null,"funder_award_id":"62473017","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":34,"referenced_works":["https://openalex.org/W2283196293","https://openalex.org/W2759136286","https://openalex.org/W2884236119","https://openalex.org/W2891076394","https://openalex.org/W2892515961","https://openalex.org/W2911450448","https://openalex.org/W2964118262","https://openalex.org/W2982316857","https://openalex.org/W2991046523","https://openalex.org/W3003265726","https://openalex.org/W3031798691","https://openalex.org/W3034563340","https://openalex.org/W3093345403","https://openalex.org/W3141797743","https://openalex.org/W3146696145","https://openalex.org/W3168892396","https://openalex.org/W3176202740","https://openalex.org/W4220825283","https://openalex.org/W4285119889","https://openalex.org/W4383108862","https://openalex.org/W4386100543","https://openalex.org/W4391855070","https://openalex.org/W4400975700","https://openalex.org/W6678830454","https://openalex.org/W6685726866","https://openalex.org/W6730038592","https://openalex.org/W6732837357","https://openalex.org/W6736572398","https://openalex.org/W6738796088","https://openalex.org/W6784646362","https://openalex.org/W6803156713","https://openalex.org/W6840380725","https://openalex.org/W6846476806","https://openalex.org/W6858722788"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"Multi-task":[0],"multi-agent":[1],"reinforcement":[2],"learning":[3,27],"(M":[4],"T-MARL)":[5],"has":[6],"recently":[7],"gained":[8],"attention":[9],"for":[10,24],"its":[11],"potential":[12],"to":[13,29,37,133],"enhance":[14],"MARL's":[15],"adaptability":[16],"across":[17],"multiple":[18],"tasks.":[19],"However,":[20],"it":[21],"is":[22,102],"challenging":[23],"existing":[25],"multi-task":[26],"methods":[28],"handle":[30,38],"complex":[31],"problems,":[32],"as":[33,104],"they":[34],"are":[35,131,152],"unable":[36],"unrelated":[39,91,122],"tasks":[40,123],"and":[41,124,137,150],"possess":[42],"limited":[43],"knowledge":[44,126],"transfer":[45,127],"capabilities.":[46,128],"In":[47],"this":[48],"paper,":[49],"we":[50,82],"propose":[51],"a":[52,64,72],"hierarchical":[53,111,146],"approach":[54,77],"that":[55,139],"efficiently":[56],"addresses":[57],"these":[58,135],"challenges.":[59],"The":[60],"high-level":[61],"module":[62,70],"utilizes":[63],"skill":[65,100],"graph,":[66],"while":[67],"the":[68,84,88,94,99,105,109,117,140,144],"low-level":[69],"employs":[71],"standard":[73,110],"MARL":[74],"algorithm.":[75],"Our":[76],"offers":[78],"two":[79],"contributions.":[80],"First,":[81],"consider":[83],"MT-MARL":[85],"problem":[86],"in":[87],"context":[89],"of":[90,96,108,116],"tasks,":[92],"expanding":[93],"scope":[95],"MTRL.":[97],"Second,":[98],"graph":[101],"used":[103],"upper":[106],"layer":[107],"approach,":[112],"with":[113],"training":[114],"independent":[115],"lower":[118],"layer,":[119],"effectively":[120],"handling":[121],"enhancing":[125],"Extensive":[129],"experiments":[130],"conducted":[132],"validate":[134],"advantages":[136],"demonstrate":[138],"proposed":[141],"method":[142],"outperforms":[143],"latest":[145],"MAPPO":[147],"algorithms.":[148],"Videos":[149],"code":[151],"available":[153],"at":[154],"<uri":[155],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[156],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/WindyLab/MT-MARL-SG</uri>":[157]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-05-31T08:46:17.908082","created_date":"2025-10-10T00:00:00"}