{"id":"https://openalex.org/W7138851081","doi":"https://doi.org/10.1609/aaai.v40i43.40997","title":"MTRL-CG: Multi-Task Reinforcement Learning Method with Spectral Clustering-Based Task Grouping","display_name":"MTRL-CG: Multi-Task Reinforcement Learning Method with Spectral Clustering-Based Task Grouping","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138851081","doi":"https://doi.org/10.1609/aaai.v40i43.40997"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i43.40997","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i43.40997","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40997/44958","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40997/44958","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007714452","display_name":"Wenjia Meng","orcid":"https://orcid.org/0000-0002-5784-7187"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenjia Meng","raw_affiliation_strings":["Shandong University"],"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130184134","display_name":"Teng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Teng Zhang","raw_affiliation_strings":["Shandong University"],"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130042109","display_name":"Haoliang Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoliang Sun","raw_affiliation_strings":["Shandong University"],"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130096147","display_name":"Yilong Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilong Yin","raw_affiliation_strings":["Shandong University"],"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007714452"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.72136388,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"43","first_page":"36723","last_page":"36731"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8931000232696533,"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":0.8931000232696533,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.009499999694526196,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.006000000052154064,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.807200014591217},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6234999895095825},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6144000291824341},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5613999962806702},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.48190000653266907},{"id":"https://openalex.org/keywords/spectral-clustering","display_name":"Spectral clustering","score":0.4733999967575073},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4277999997138977},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.38690000772476196}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.807200014591217},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.751800000667572},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6234999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6186000108718872},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6144000291824341},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5613999962806702},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5446000099182129},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.48190000653266907},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.4733999967575073},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4277999997138977},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.320499986410141},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i43.40997","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i43.40997","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40997/44958","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i43.40997","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i43.40997","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40997/44958","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G261340674","display_name":null,"funder_award_id":"62206158","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2802911279","display_name":null,"funder_award_id":"Young","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2954701993","display_name":null,"funder_award_id":"ZR2022","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3817879578","display_name":null,"funder_award_id":"ZR2022QF097","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320311026","display_name":"Shandong University","ror":"https://ror.org/0207yh398"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138851081.pdf","grobid_xml":"https://content.openalex.org/works/W7138851081.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-task":[0],"reinforcement":[1,65],"learning":[2,66,89],"(RL)":[3],"aims":[4],"to":[5,46,54,78,90,117,126,145],"enhance":[6],"agent":[7],"performance":[8],"across":[9,25],"multiple":[10],"tasks":[11,27,81,128],"by":[12,99],"enabling":[13,86],"effective":[14],"knowledge":[15],"transfer.":[16],"However,":[17],"these":[18,119],"methods":[19],"adopt":[20],"a":[21,63,109,141],"fully":[22],"shared":[23,110],"policy":[24,88,143],"all":[26],"without":[28],"explicitly":[29],"distinguishing":[30],"between":[31],"related":[32,80],"and":[33,52,82,112,132],"conflicting":[34,84],"ones,":[35,85],"making":[36],"them":[37],"suffer":[38],"from":[39],"negative":[40,92],"interference":[41],"issue,":[42],"where":[43],"updates":[44,105],"beneficial":[45],"one":[47],"task":[48,71,136],"adversely":[49],"affect":[50],"others":[51,107],"lead":[53],"degraded":[55],"overall":[56],"performance.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61],"propose":[62],"multi-task":[64,164],"method":[67],"with":[68,140],"spectral":[69,76,130],"clustering-based":[70],"grouping":[72],"(MTRL-CG),":[73],"which":[74],"leverages":[75],"clustering":[77,122],"group":[79,137],"separate":[83],"group-wise":[87],"mitigate":[91],"interference.":[93],"We":[94],"first":[95],"quantify":[96],"inter-task":[97],"affinity":[98,115],"measuring":[100],"the":[101,151,170,174,177],"influence":[102],"of":[103,176],"task-specific":[104],"on":[106,169],"within":[108],"model,":[111],"construct":[113],"an":[114],"matrix":[116],"capture":[118],"relationships.":[120],"Spectral":[121],"is":[123,138],"then":[124],"applied":[125],"partition":[127],"via":[129],"embedding":[131],"k-means":[133],"clustering.":[134],"Each":[135],"trained":[139],"dedicated":[142],"network":[144],"promote":[146],"focused":[147],"learning.":[148],"Built":[149],"upon":[150],"Soft":[152],"Actor-Critic":[153],"(SAC)":[154],"algorithm,":[155],"MTRL-CG":[156,179],"can":[157],"be":[158],"readily":[159],"integrated":[160],"into":[161],"existing":[162],"SAC-based":[163],"RL":[165],"methods.":[166],"Extensive":[167],"experiments":[168],"Meta-World":[171],"benchmark":[172],"demonstrate":[173],"effectiveness":[175],"proposed":[178],"method.":[180]},"counts_by_year":[],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2026-03-20T00:00:00"}