{"id":"https://openalex.org/W4311925376","doi":"https://doi.org/10.1109/iccsi55536.2022.9970593","title":"Knowledge Transfer in Multi-Agent Reinforcement Learning Using Decision Trees","display_name":"Knowledge Transfer in Multi-Agent Reinforcement Learning Using Decision Trees","publication_year":2022,"publication_date":"2022-11-18","ids":{"openalex":"https://openalex.org/W4311925376","doi":"https://doi.org/10.1109/iccsi55536.2022.9970593"},"language":"en","primary_location":{"id":"doi:10.1109/iccsi55536.2022.9970593","doi":"https://doi.org/10.1109/iccsi55536.2022.9970593","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccsi55536.2022.9970593","pdf_url":null,"source":{"id":"https://openalex.org/S4363608341","display_name":"International Conference on Cyber-Physical Social Intelligence (ICCSI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Cyber-Physical Social Intelligence (ICCSI)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5100533956","display_name":"Jingyuan Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyuan Guo","raw_affiliation_strings":["Nanjing University,Department of Control and Systems Engineering,Nanjing,China","Department of Control and Systems Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,Department of Control and Systems Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Department of Control and Systems Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021451616","display_name":"Yuanyang Zhu","orcid":"https://orcid.org/0000-0001-7484-1804","observed_orcids":["https://orcid.org/0000-0001-7484-1804"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyang Zhu","raw_affiliation_strings":["Nanjing University,Department of Control and Systems Engineering,Nanjing,China","Department of Control and Systems Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,Department of Control and Systems Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Department of Control and Systems Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100697167","display_name":"Chunlin Chen","orcid":"https://orcid.org/0000-0003-3929-4707","observed_orcids":["https://orcid.org/0000-0003-3929-4707"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlin Chen","raw_affiliation_strings":["Nanjing University,Department of Control and Systems Engineering,Nanjing,China","Department of Control and Systems Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,Department of Control and Systems Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Department of Control and Systems Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10380414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"96","issue":null,"first_page":"256","last_page":"261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0,"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/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.9380000233650208},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"knowledge transfer","score":0.9940000176429749},{"id":"https://openalex.org/keywords/decision-tree","display_name":"decision tree","score":0.9229999780654907},{"id":"https://openalex.org/keywords/expert-policy","display_name":"expert policy","score":0.8289999961853027},{"id":"https://openalex.org/keywords/trajectory-generation","display_name":"trajectory generation","score":0.6389999985694885},{"id":"https://openalex.org/keywords/agent-coordination","display_name":"agent coordination","score":0.6859999895095825}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8886513710021973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8100448846817017},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6572864651679993},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6516603827476501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6156907081604004},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.5666085481643677},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.5535286068916321},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.497731477022171},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4544459283351898},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.44975677132606506},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4347786009311676},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.23046159744262695},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12784653902053833},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccsi55536.2022.9970593","doi":"https://doi.org/10.1109/iccsi55536.2022.9970593","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccsi55536.2022.9970593","pdf_url":null,"source":{"id":"https://openalex.org/S4363608341","display_name":"International Conference on Cyber-Physical Social Intelligence (ICCSI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Cyber-Physical Social Intelligence (ICCSI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7996831764","display_name":null,"funder_award_id":"62073160","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":13,"referenced_works":["https://openalex.org/W1483135265","https://openalex.org/W1570329253","https://openalex.org/W1574700590","https://openalex.org/W1576962511","https://openalex.org/W1587866709","https://openalex.org/W1597303641","https://openalex.org/W2050829396","https://openalex.org/W2131600418","https://openalex.org/W2148292332","https://openalex.org/W2149043954","https://openalex.org/W2372175702","https://openalex.org/W4297957988","https://openalex.org/W7053319657"],"related_works":["https://openalex.org/W2397927371","https://openalex.org/W1457482454","https://openalex.org/W4280521017","https://openalex.org/W7084039771","https://openalex.org/W2945579124","https://openalex.org/W4252318465","https://openalex.org/W2921955147","https://openalex.org/W4390306666","https://openalex.org/W2018629084","https://openalex.org/W4399354141"],"abstract_inverted_index":{"Multi-agent":[0],"reinforcement":[1,80,139],"learning":[2,14,31,81,140],"has":[3,141],"achieved":[4],"promising":[5],"progress":[6],"in":[7],"a":[8,15,38,52,69,78],"range":[9],"of":[10,103,137],"real-world":[11],"tasks.":[12,121],"However,":[13],"model":[16],"from":[17,51],"scratch":[18],"for":[19,25],"every":[20],"new":[21,39],"task":[22],"largely":[23],"struggles":[24],"the":[26,49,57,60,63,86,91,96,101,110,115,119,135],"optimal":[27],"policy":[28,76,93],"requiring":[29],"more":[30],"processes.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36,67,89,108],"propose":[37],"method":[40,131],"that":[41,126],"realizes":[42],"robust":[43],"coordination":[44],"knowledge":[45,50,112,130],"transfer":[46,102,129],"by":[47],"extracting":[48],"single":[53,70],"agent":[54,58,71],"and":[55,134],"guiding":[56],"executes":[59],"action":[61],"during":[62],"early":[64],"stage.":[65],"First,":[66],"train":[68],"to":[72,94,99,113],"obtain":[73],"an":[74],"expert":[75,87,92],"with":[77],"deep":[79],"algorithm.":[82],"Then,":[83],"after":[84],"getting":[85],"policy,":[88],"utilize":[90,109],"generate":[95],"trajectories":[97],"experience":[98],"extract":[100],"domain":[104],"control":[105],"knowledge.":[106],"Finally,":[107],"extracted":[111],"guide":[114],"multi-agents":[116],"quickly":[117],"adapt":[118],"complex":[120],"The":[122],"experimental":[123],"results":[124],"demonstrate":[125],"our":[127],"proposed":[128],"is":[132],"effective,":[133],"efficiency":[136],"multi-agent":[138],"been":[142],"considerably":[143],"improved.":[144]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2023-01-02T00:00:00"}