{"id":"https://openalex.org/W4385551639","doi":"https://doi.org/10.1007/s11280-023-01197-5","title":"Neural-network-based parameter tuning for multi-agent simulation using deep reinforcement learning","display_name":"Neural-network-based parameter tuning for multi-agent simulation using deep reinforcement learning","publication_year":2023,"publication_date":"2023-08-03","ids":{"openalex":"https://openalex.org/W4385551639","doi":"https://doi.org/10.1007/s11280-023-01197-5"},"language":"en","primary_location":{"id":"doi:10.1007/s11280-023-01197-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11280-023-01197-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11280-023-01197-5.pdf","source":{"id":"https://openalex.org/S129236917","display_name":"World Wide Web","issn_l":"1386-145X","issn":["1386-145X","1573-1413"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"World Wide Web","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11280-023-01197-5.pdf","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":true,"raw_author_name":"Masanori Hirano","raw_affiliation_strings":["School of Engineering, The University of Tokyo, 7-3-1, Hongo, Bunkyo, Tokyo, 113-8656, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, The University of Tokyo, 7-3-1, Hongo, Bunkyo, Tokyo, 113-8656, 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":["School of Engineering, The University of Tokyo, 7-3-1, Hongo, Bunkyo, Tokyo, 113-8656, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, The University of Tokyo, 7-3-1, Hongo, Bunkyo, Tokyo, 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002301422"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.2355,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57249993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"26","issue":"5","first_page":"3535","last_page":"3559"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9944999814033508,"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":0.9944999814033508,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9926999807357788,"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/T11270","display_name":"Complex Systems and Time Series Analysis","score":0.9926000237464905,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8687681555747986},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8213748931884766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6046955585479736},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.585661768913269},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5623727440834045},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5337923765182495},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5225552916526794},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4637036919593811},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.07833865284919739}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8687681555747986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8213748931884766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6046955585479736},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.585661768913269},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5623727440834045},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5337923765182495},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5225552916526794},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4637036919593811},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.07833865284919739},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11280-023-01197-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11280-023-01197-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11280-023-01197-5.pdf","source":{"id":"https://openalex.org/S129236917","display_name":"World Wide Web","issn_l":"1386-145X","issn":["1386-145X","1573-1413"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"World Wide Web","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11280-023-01197-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11280-023-01197-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11280-023-01197-5.pdf","source":{"id":"https://openalex.org/S129236917","display_name":"World Wide Web","issn_l":"1386-145X","issn":["1386-145X","1573-1413"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"World Wide Web","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3857278492","display_name":null,"funder_award_id":"JP 21J20074","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320322832","display_name":"University of Tokyo","ror":"https://ror.org/057zh3y96"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385551639.pdf"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1537415400","https://openalex.org/W1541508341","https://openalex.org/W1905823147","https://openalex.org/W1966838679","https://openalex.org/W1980620643","https://openalex.org/W2017957151","https://openalex.org/W2026600711","https://openalex.org/W2032774582","https://openalex.org/W2050032417","https://openalex.org/W2057537221","https://openalex.org/W2064675550","https://openalex.org/W2121681609","https://openalex.org/W2131600418","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2173248099","https://openalex.org/W2236108379","https://openalex.org/W2260297278","https://openalex.org/W2273968408","https://openalex.org/W2317512990","https://openalex.org/W2547939421","https://openalex.org/W2618530766","https://openalex.org/W2619020317","https://openalex.org/W2724169821","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2766447205","https://openalex.org/W2781726626","https://openalex.org/W2786928559","https://openalex.org/W2805003733","https://openalex.org/W2902907165","https://openalex.org/W2904246096","https://openalex.org/W2949676527","https://openalex.org/W2964046286","https://openalex.org/W2973525135","https://openalex.org/W3017026466","https://openalex.org/W3021485039","https://openalex.org/W3033083249","https://openalex.org/W3040394052","https://openalex.org/W3041202696","https://openalex.org/W3104765064","https://openalex.org/W3124980136","https://openalex.org/W3125993863","https://openalex.org/W3139377883","https://openalex.org/W4211225168","https://openalex.org/W4214717370","https://openalex.org/W4250153073"],"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/W2043093291","https://openalex.org/W2101155126","https://openalex.org/W2363545964"],"abstract_inverted_index":{"Abstract":[0],"This":[1,42],"study":[2,43],"proposes":[3,44],"a":[4,21,111,118,126,181],"new":[5],"efficient":[6,45],"parameter":[7,40,46,127],"tuning":[8,47,62,128,159],"method":[9,66,169,209],"for":[10,24,39,93],"multi-agent":[11],"simulation":[12],"(MAS)":[13],"using":[14,52],"deep":[15,53,69,74],"reinforcement":[16,54,70],"learning.":[17],"MAS":[18],"is":[19,28,219],"currently":[20],"useful":[22],"tool":[23],"social":[25],"sciences,":[26],"but":[27],"hard":[29],"to":[30,35,48,85,102,197],"realize":[31],"realistic":[32],"simulations":[33],"due":[34],"its":[36,140],"computational":[37],"burden":[38],"tuning.":[41],"address":[49],"this":[50],"issue":[51],"learning":[55],"methods.":[56],"To":[57],"improve":[58],"compatibility":[59],"with":[60],"the":[61,86,104,143,154,163,167,173,191,195,199,207,211,222],"task,":[63,95],"our":[64,94,137,151,176],"proposed":[65,138,168],"employs":[67],"actor-critic-based":[68],"learning,":[71],"such":[72],"as":[73,180,186],"deterministic":[75],"policy":[76],"gradient":[77],"(DDPG)":[78],"and":[79,91,117,142,213],"soft":[80],"actor-critic":[81],"(SAC).":[82],"In":[83],"addition":[84],"customized":[87],"version":[88],"of":[89,158,166,175,190,226],"DDPG":[90],"SAC":[92],"we":[96,124,217],"also":[97,204],"propose":[98],"three":[99],"additional":[100,164],"components":[101,165],"stabilize":[103],"learning:":[105],"an":[106,131,187],"action":[107],"converter":[108],"(DDPG":[109],"only),":[110],"redundant":[112],"full":[113],"neural":[114],"network":[115],"actor,":[116],"seed":[119],"fixer.":[120],"For":[121],"experimental":[122],"verification,":[123],"employ":[125],"task":[129],"in":[130,156],"artificial":[132],"financial":[133],"market":[134],"simulation,":[135,192],"comparing":[136],"model,":[139,183],"ablations,":[141],"Bayesian":[144],"estimation-based":[145],"baseline.":[146],"The":[147],"results":[148],"demonstrate":[149],"that":[150,162,184,206],"model":[152,177],"outperforms":[153],"baseline":[155],"terms":[157],"performance,":[160],"indicating":[161],"are":[170],"essential.":[171],"Moreover,":[172],"critic":[174],"works":[178],"effectively":[179],"surrogate":[182],"is,":[185],"approximate":[188],"function":[189],"which":[193,216],"allows":[194],"actor":[196],"tune":[198],"parameters":[200],"appropriately.":[201],"We":[202],"have":[203],"found":[205],"SAC-based":[208],"exhibits":[210],"best":[212],"fastest":[214],"convergence,":[215],"assume":[218],"achieved":[220],"by":[221],"high":[223],"exploration":[224],"capability":[225],"SAC.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}