{"id":"https://openalex.org/W4313203316","doi":"https://doi.org/10.1109/besc57393.2022.9995509","title":"Parameter Tuning Method for Multi-agent Simulation using Reinforcement Learning","display_name":"Parameter Tuning Method for Multi-agent Simulation using Reinforcement Learning","publication_year":2022,"publication_date":"2022-10-29","ids":{"openalex":"https://openalex.org/W4313203316","doi":"https://doi.org/10.1109/besc57393.2022.9995509"},"language":"en","primary_location":{"id":"doi:10.1109/besc57393.2022.9995509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/besc57393.2022.9995509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 9th International Conference on Behavioural and Social Computing (BESC)","raw_type":"proceedings-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/A5002301422","display_name":"Masanori Hirano","orcid":"https://orcid.org/0000-0001-5883-8250"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masanori Hirano","raw_affiliation_strings":["The University of Tokyo,School of Engineering,Tokyo,Japan","School of Engineering, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,School of Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"School of Engineering, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044205949","display_name":"Kiyoshi Izumi","orcid":"https://orcid.org/0000-0003-0870-7310"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kiyoshi Izumi","raw_affiliation_strings":["The University of Tokyo,School of Engineering,Tokyo,Japan","School of Engineering, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,School of Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"School of Engineering, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3379,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64816831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9943000078201294,"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"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9943000078201294,"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"}},{"id":"https://openalex.org/T11270","display_name":"Complex Systems and Time Series Analysis","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8561984896659851},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6965311169624329},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6864909529685974},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6128166317939758},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6069191694259644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5089058876037598},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4867746829986572},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.41590744256973267},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3981628119945526},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12369582056999207}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8561984896659851},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6965311169624329},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6864909529685974},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6128166317939758},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6069191694259644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5089058876037598},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4867746829986572},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.41590744256973267},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3981628119945526},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12369582056999207},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/besc57393.2022.9995509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/besc57393.2022.9995509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 9th International Conference on Behavioural and Social Computing (BESC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1537415400","https://openalex.org/W1541508341","https://openalex.org/W1966838679","https://openalex.org/W1980620643","https://openalex.org/W2017957151","https://openalex.org/W2050032417","https://openalex.org/W2121681609","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2171872009","https://openalex.org/W2236108379","https://openalex.org/W2260297278","https://openalex.org/W2273968408","https://openalex.org/W2317512990","https://openalex.org/W2547939421","https://openalex.org/W2560674852","https://openalex.org/W2619020317","https://openalex.org/W2724169821","https://openalex.org/W2746553466","https://openalex.org/W2904246096","https://openalex.org/W2949676527","https://openalex.org/W2964046286","https://openalex.org/W3017026466","https://openalex.org/W3021485039","https://openalex.org/W3040394052","https://openalex.org/W3104765064","https://openalex.org/W3118460252","https://openalex.org/W3139377883","https://openalex.org/W3150455482","https://openalex.org/W4211225168","https://openalex.org/W6684921986","https://openalex.org/W6688102288","https://openalex.org/W6740092555","https://openalex.org/W6747473740","https://openalex.org/W6751979845","https://openalex.org/W6757592117","https://openalex.org/W6767919266"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2043093291","https://openalex.org/W2363545964"],"abstract_inverted_index":{"This":[0],"study":[1],"proposes":[2],"a":[3,17,40,58,65,73,89,128],"reinforcement-learning-based":[4],"method":[5,36,85,117],"for":[6],"efficient":[7],"parameter":[8],"tuning":[9,105],"in":[10,52,76,102],"multi-agent":[11],"simulations":[12],"(MAS).":[13],"MAS":[14],"usually":[15],"has":[16,47],"high":[18],"computational":[19],"burden":[20],"because":[21],"of":[22,104,114,123,137],"the":[23,100,110,115,121,138,142,147],"agents;":[24],"thus,":[25],"it":[26],"is":[27,37],"important":[28],"to":[29,98,144],"tune":[30,146],"its":[31],"parameters":[32],"efficiently.":[33],"Our":[34],"proposed":[35,51,116],"based":[38],"on":[39],"deep":[41],"deterministic":[42],"policy":[43],"gradient":[44],"(DDPG)":[45],"and":[46,64,107],"three":[48,111],"additional":[49,112],"components":[50,113],"this":[53],"study:":[54],"an":[55,69,77,134],"action":[56],"converter,":[57],"redundant":[59],"full":[60],"neural":[61],"network":[62],"actor,":[63],"seed":[66],"fixer.":[67],"As":[68],"experiment,":[70],"we":[71],"employed":[72,87],"parameter-tuning":[74],"task":[75],"artificial":[78],"financial":[79],"market":[80],"simulation.":[81],"A":[82],"Bayesian":[83],"estimation-based":[84],"was":[86],"as":[88,127,133],"baseline.":[90],"The":[91],"results":[92],"show":[93],"that":[94,109,131],"our":[95],"model":[96],"tends":[97],"outperform":[99],"baseline":[101],"terms":[103],"performance":[106],"indicate":[108],"are":[118],"essential.":[119],"Moreover,":[120],"critic":[122],"DDPG":[124],"effectively":[125],"functions":[126],"surrogate":[129],"model,":[130],"is,":[132],"approximate":[135],"function":[136],"simulation,":[139],"which":[140],"allows":[141],"actor":[143],"appropriately":[145],"parameters.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}