{"id":"https://openalex.org/W7165395166","doi":"https://doi.org/10.1016/j.knosys.2026.116499","title":"TAPPS: Learning diverse policies via task-adaptive partial parameter sharing in heterogeneous multi-agent reinforcement learning","display_name":"TAPPS: Learning diverse policies via task-adaptive partial parameter sharing in heterogeneous multi-agent reinforcement learning","publication_year":2026,"publication_date":"2026-06-19","ids":{"openalex":"https://openalex.org/W7165395166","doi":"https://doi.org/10.1016/j.knosys.2026.116499"},"language":"en","primary_location":{"id":"doi:10.1016/j.knosys.2026.116499","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.116499","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based 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/A5100714261","display_name":"Mengke Wang","orcid":"https://orcid.org/0000-0002-4521-194X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengke Wang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0002-5757-8674","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139024620","display_name":"Han Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102944236","display_name":"Zijian Zhou","orcid":"https://orcid.org/0000-0003-3315-3962"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zijian Zhou","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0001-3728-0507","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101902939","display_name":"Zhenyu Zhang","orcid":"https://orcid.org/0000-0002-9470-7132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenyu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027437331","display_name":"Luo Xiangfeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangfeng Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138993960","display_name":"Shaorong Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaorong Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3130,"currency":"USD","value_usd":3130},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79329313,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"349","issue":null,"first_page":"116499","last_page":"116499"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9641000032424927,"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":0.9641000032424927,"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":0.0066999997943639755,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0026000000070780516,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6025000214576721},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.3422999978065491},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.32829999923706055},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.3098999857902527},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.2849000096321106},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.272599995136261}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6025000214576721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5928999781608582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45210000872612},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29339998960494995},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.knosys.2026.116499","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.116499","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1641379095","https://openalex.org/W2062882942","https://openalex.org/W2072169887","https://openalex.org/W2096145798","https://openalex.org/W2153469952","https://openalex.org/W2807741983","https://openalex.org/W2913662073","https://openalex.org/W2991046523","https://openalex.org/W4310705874","https://openalex.org/W4385061644","https://openalex.org/W4385767524","https://openalex.org/W4387692896","https://openalex.org/W4388819818","https://openalex.org/W4389987589","https://openalex.org/W4390638728","https://openalex.org/W4391070002","https://openalex.org/W4400792723","https://openalex.org/W4405873421","https://openalex.org/W4407393094","https://openalex.org/W4409261422","https://openalex.org/W4411343117","https://openalex.org/W4416842115","https://openalex.org/W7124265438","https://openalex.org/W7124270508","https://openalex.org/W7124323643","https://openalex.org/W7124329025","https://openalex.org/W7133186185","https://openalex.org/W7133196695","https://openalex.org/W7133225323","https://openalex.org/W7133226216","https://openalex.org/W7133246398"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-24T06:17:17.354583","created_date":"2026-06-20T00:00:00"}