{"id":"https://openalex.org/W4206054900","doi":"https://doi.org/10.1109/lcomm.2022.3144451","title":"Trustable Policy Collaboration Scheme for Multi-Agent Stigmergic Reinforcement Learning","display_name":"Trustable Policy Collaboration Scheme for Multi-Agent Stigmergic Reinforcement Learning","publication_year":2022,"publication_date":"2022-01-18","ids":{"openalex":"https://openalex.org/W4206054900","doi":"https://doi.org/10.1109/lcomm.2022.3144451"},"language":"en","primary_location":{"id":"doi:10.1109/lcomm.2022.3144451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcomm.2022.3144451","pdf_url":null,"source":{"id":"https://openalex.org/S147316732","display_name":"IEEE Communications Letters","issn_l":"1089-7798","issn":["1089-7798","1558-2558","2373-7891"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316002","host_organization_name":"IEEE Communications Society","host_organization_lineage":["https://openalex.org/P4310316002","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Communications Society","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 Communications 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/A5027890741","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0003-4564-470X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4564-470X","affiliations":[{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014842979","display_name":"Rongpeng Li","orcid":"https://orcid.org/0000-0003-4297-5060"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongpeng Li","raw_affiliation_strings":["College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4297-5060","affiliations":[{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036831868","display_name":"Zhifeng Zhao","orcid":"https://orcid.org/0000-0002-5479-7890"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifeng Zhao","raw_affiliation_strings":["Zhejiang Laboratory, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5479-7890","affiliations":[{"raw_affiliation_string":"Zhejiang Laboratory, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100626780","display_name":"Honggang Zhang","orcid":"https://orcid.org/0000-0003-1492-1364"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honggang Zhang","raw_affiliation_strings":["College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1492-1364","affiliations":[{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6561,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.72451628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"26","issue":"4","first_page":"823","last_page":"827"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965000152587891,"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":0.9965000152587891,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9897000193595886,"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/T10524","display_name":"Traffic control and management","score":0.9847999811172485,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8071196675300598},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.7843620777130127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7369282245635986},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.63846355676651},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.5984514951705933},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.5632498860359192},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.5507711172103882},{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.5378920435905457},{"id":"https://openalex.org/keywords/autonomy","display_name":"Autonomy","score":0.4891345798969269},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4688364565372467},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.465913325548172},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3577224314212799},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35200315713882446},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16234034299850464},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1510850489139557},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09446674585342407}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8071196675300598},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.7843620777130127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7369282245635986},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.63846355676651},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.5984514951705933},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.5632498860359192},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.5507711172103882},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.5378920435905457},{"id":"https://openalex.org/C65414064","wikidata":"https://www.wikidata.org/wiki/Q484105","display_name":"Autonomy","level":2,"score":0.4891345798969269},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4688364565372467},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.465913325548172},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3577224314212799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35200315713882446},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16234034299850464},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1510850489139557},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09446674585342407},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lcomm.2022.3144451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcomm.2022.3144451","pdf_url":null,"source":{"id":"https://openalex.org/S147316732","display_name":"IEEE Communications Letters","issn_l":"1089-7798","issn":["1089-7798","1558-2558","2373-7891"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316002","host_organization_name":"IEEE Communications Society","host_organization_lineage":["https://openalex.org/P4310316002","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Communications Society","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 Communications Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5459816226","display_name":"\u57fa\u4e8e\u4e1a\u52a1\u611f\u77e5\u7684\u5185\u751f\u667a\u80fd\u901a\u4fe1\u7f51\u7edc\u7814\u7a76","funder_award_id":"62071425","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7209202450","display_name":null,"funder_award_id":"2020YFB1804800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G797825634","display_name":"\u57fa\u4e8e\u7528\u6237\u884c\u4e3a\u9884\u6d4b\u7684\u65e0\u7ebf\u8fb9\u7f18\u7f51\u7edc\u8d44\u6e90\u5229\u7528\u7406\u8bba\u7814\u7a76","funder_award_id":"61731002","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":12,"referenced_works":["https://openalex.org/W1641379095","https://openalex.org/W1970789124","https://openalex.org/W2096145798","https://openalex.org/W2099618002","https://openalex.org/W2736601468","https://openalex.org/W3122551441","https://openalex.org/W3131448887","https://openalex.org/W4380078504","https://openalex.org/W6634413486","https://openalex.org/W6638018090","https://openalex.org/W6741002519","https://openalex.org/W6755921573"],"related_works":["https://openalex.org/W4321204549","https://openalex.org/W4293149836","https://openalex.org/W4360764167","https://openalex.org/W266446692","https://openalex.org/W4327810432","https://openalex.org/W3004584758","https://openalex.org/W4318719223","https://openalex.org/W2042849989","https://openalex.org/W2934281059","https://openalex.org/W4206054900"],"abstract_inverted_index":{"In":[0,71],"this":[1,79],"letter,":[2],"we":[3,73],"propose":[4],"a":[5,75,89],"trustable":[6,20,52,80],"policy":[7,21,30,49,53,81],"collaboration":[8,22,54,82],"scheme":[9,23,55],"in":[10,88],"the":[11,29,41,48,58,67,96],"paradigm":[12],"of":[13,32,40,61,69,78],"multi-agent":[14],"independent":[15],"reinforcement":[16],"learning":[17],"(MAIRL).":[18],"This":[19,51],"is":[24,44],"realized":[25],"by":[26],"directly":[27],"mixing":[28],"parameters":[31],"homogeneous":[33],"agents,":[34],"for":[35],"which":[36],"an":[37],"upper":[38],"bound":[39],"mixture":[42],"metric":[43],"derived":[45],"to":[46],"guarantee":[47],"improvement.":[50],"can":[56],"update":[57],"behavioral":[59],"policies":[60],"agents":[62],"distributedly":[63],"and":[64,84],"further":[65],"improve":[66],"performance":[68,97],"MAIRL.":[70],"addition,":[72],"develop":[74],"practical":[76],"implementation":[77],"scheme,":[83],"verify":[85],"its":[86],"effectiveness":[87],"mixed-autonomy":[90],"traffic":[91],"control":[92],"simulation":[93],"scenario":[94],"through":[95],"comparison":[98],"with":[99],"other":[100],"typical":[101],"methods.":[102]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}