{"id":"https://openalex.org/W4400975935","doi":"https://doi.org/10.1109/icca62789.2024.10591854","title":"Continuous-Time Distributed Dynamic Programming for Networked Multi-Agent Markov Decision Processes","display_name":"Continuous-Time Distributed Dynamic Programming for Networked Multi-Agent Markov Decision Processes","publication_year":2024,"publication_date":"2024-06-18","ids":{"openalex":"https://openalex.org/W4400975935","doi":"https://doi.org/10.1109/icca62789.2024.10591854"},"language":"en","primary_location":{"id":"doi:10.1109/icca62789.2024.10591854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca62789.2024.10591854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 18th International Conference on Control & Automation (ICCA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100654317","display_name":"Donghwan Lee","orcid":"https://orcid.org/0000-0002-4962-8478"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Donghwan Lee","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),Department of Electrical and Engineering,Daejeon,South Korea,34141"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),Department of Electrical and Engineering,Daejeon,South Korea,34141","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006683710","display_name":"Han-Dong Lim","orcid":"https://orcid.org/0000-0002-1515-5836"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Han-Dong Lim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),Department of Electrical and Engineering,Daejeon,South Korea,34141"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),Department of Electrical and Engineering,Daejeon,South Korea,34141","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074697684","display_name":"Do Wan Kim","orcid":"https://orcid.org/0000-0002-4176-2082"},"institutions":[{"id":"https://openalex.org/I145808223","display_name":"Hanbat National University","ror":"https://ror.org/00x514t95","country_code":"KR","type":"education","lineage":["https://openalex.org/I145808223"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Do Wan Kim","raw_affiliation_strings":["Hanbat National University,Department of Electrical Engineering,Daejeon,South Korea,34158"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanbat National University,Department of Electrical Engineering,Daejeon,South Korea,34158","institution_ids":["https://openalex.org/I145808223"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"960","last_page":"967"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9437000155448914,"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":0.9437000155448914,"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/markov-decision-process","display_name":"Markov decision process","score":0.8228719234466553},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7822558283805847},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5626797080039978},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5554594993591309},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5414095520973206},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4156387150287628},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1966899335384369},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08992955088615417},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08579114079475403}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8228719234466553},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7822558283805847},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5626797080039978},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5554594993591309},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5414095520973206},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4156387150287628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1966899335384369},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08992955088615417},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08579114079475403},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icca62789.2024.10591854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca62789.2024.10591854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 18th International Conference on Control & Automation (ICCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4253661243","display_name":null,"funder_award_id":"NRF-2021R1I1A3058581","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W86892992","https://openalex.org/W1486993561","https://openalex.org/W1499021337","https://openalex.org/W1571416372","https://openalex.org/W2020123437","https://openalex.org/W2026509976","https://openalex.org/W2071983464","https://openalex.org/W2075268401","https://openalex.org/W2100677568","https://openalex.org/W2114791779","https://openalex.org/W2144672231","https://openalex.org/W2165744313","https://openalex.org/W2493209382","https://openalex.org/W2504148212","https://openalex.org/W2964005211","https://openalex.org/W2966162740","https://openalex.org/W2991046523","https://openalex.org/W3006742932","https://openalex.org/W3023368031","https://openalex.org/W3027121709","https://openalex.org/W3119982186","https://openalex.org/W4205326910","https://openalex.org/W4214717370","https://openalex.org/W4312657794","https://openalex.org/W4382064684","https://openalex.org/W6603582964","https://openalex.org/W6703110798","https://openalex.org/W6751921135","https://openalex.org/W6762191990","https://openalex.org/W6766912882","https://openalex.org/W6774313945","https://openalex.org/W6785894376","https://openalex.org/W6795085760"],"related_works":["https://openalex.org/W4389475841","https://openalex.org/W4241327272","https://openalex.org/W2120406836","https://openalex.org/W1996214847","https://openalex.org/W2903299703","https://openalex.org/W2117282672","https://openalex.org/W4211224558","https://openalex.org/W4281791088","https://openalex.org/W2119790124","https://openalex.org/W4385342861"],"abstract_inverted_index":{"The":[0,98,111],"main":[1],"goal":[2],"of":[3,46,83,100],"this":[4,114],"paper":[5,115],"is":[6,92,104],"to":[7,37,55],"investigate":[8],"continuous-time":[9],"distributed":[10,28,75,80,90,121],"dynamic":[11],"programming":[12],"(DP)":[13],"algorithms":[14,103],"for":[15,119],"networked":[16],"multi-agent":[17,29],"Markov":[18],"decision":[19],"problems":[20],"(MAMDPs).":[21],"In":[22],"our":[23],"study,":[24],"we":[25],"adopt":[26],"a":[27,63,68,73,88,95],"framework":[30],"where":[31],"individual":[32],"agents":[33,61],"have":[34],"access":[35],"only":[36],"their":[38],"own":[39],"rewards,":[40],"lacking":[41],"insights":[42],"into":[43],"the":[44,53,79,101,117],"rewards":[45],"other":[47],"agents.":[48],"Moreover,":[49],"each":[50],"agent":[51],"has":[52],"ability":[54],"share":[56],"its":[57],"parameters":[58],"with":[59],"neighboring":[60],"through":[62,94,106],"communication":[64],"network,":[65],"represented":[66],"by":[67,78],"graph.":[69],"We":[70],"first":[71],"introduce":[72],"novel":[74],"DP,":[76],"inspired":[77],"optimization":[81],"method":[82],"Wang":[84],"and":[85,108],"Elia.":[86],"Next,":[87],"new":[89,120],"DP":[91,102],"introduced":[93],"decoupling":[96],"process.":[97],"convergence":[99],"proved":[105],"systems":[107],"control":[109],"perspectives.":[110],"study":[112],"in":[113],"sets":[116],"stage":[118],"temporal":[122],"different":[123],"learning":[124],"algorithms.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}