{"id":"https://openalex.org/W1899613237","doi":"https://doi.org/10.1109/cdc.2003.1272486","title":"A distributed algorithm for solving a class of multi-agent Markov decision problems","display_name":"A distributed algorithm for solving a class of multi-agent Markov decision problems","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W1899613237","doi":"https://doi.org/10.1109/cdc.2003.1272486","mag":"1899613237"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2003.1272486","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2003.1272486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://drum.lib.umd.edu/bitstreams/2a229841-84d2-4708-8a5f-46ea843efb4d/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041693183","display_name":"Hyeong Soo Chang","orcid":"https://orcid.org/0000-0003-3298-0018"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeong Soo Chang","raw_affiliation_strings":["Dept. of Comput. Sci. & Eng., Sogang Univ., Seoul, South Korea","Dept. of Computer Science & Engineering, Sogang University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Sogang Univ., Seoul, South Korea","institution_ids":["https://openalex.org/I148751991"]},{"raw_affiliation_string":"Dept. of Computer Science & Engineering, Sogang University, Seoul, South Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000889975","display_name":"Michael C. Fu","orcid":"https://orcid.org/0000-0003-2105-4932"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M.C. Fu","raw_affiliation_strings":["Robert H. Smith School of Business and Institute for Systems Research, University of Maryland, College Park, MD, USA","University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robert H. Smith School of Business and Institute for Systems Research, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5341","last_page":"5346 Vol.5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12288","display_name":"Optimization and Search Problems","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9929999709129333,"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/markov-decision-process","display_name":"Markov decision process","score":0.7857910394668579},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6456535458564758},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6428695917129517},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5635522603988647},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5421804189682007},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.537661612033844},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4826293885707855},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4597610831260681},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.45434874296188354},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4124712347984314},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3239920139312744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26855069398880005},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12854105234146118}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7857910394668579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6456535458564758},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6428695917129517},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5635522603988647},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5421804189682007},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.537661612033844},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4826293885707855},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4597610831260681},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.45434874296188354},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4124712347984314},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3239920139312744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26855069398880005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12854105234146118},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cdc.2003.1272486","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2003.1272486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475)","raw_type":"proceedings-article"},{"id":"pmh:oai:drum.lib.umd.edu:1903/6357","is_oa":true,"landing_page_url":"http://hdl.handle.net/1903/6357","pdf_url":"https://drum.lib.umd.edu/bitstreams/2a229841-84d2-4708-8a5f-46ea843efb4d/download","source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Technical Report"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.840.8080","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.840.8080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://drum.lib.umd.edu/bitstream/handle/1903/6357/TR_2003-25.pdf%3Bjsessionid%3D43F3FB489F8D7A15F388C1FC5B1B0FF1?sequence%3D1","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:drum.lib.umd.edu:1903/6357","is_oa":true,"landing_page_url":"http://hdl.handle.net/1903/6357","pdf_url":"https://drum.lib.umd.edu/bitstreams/2a229841-84d2-4708-8a5f-46ea843efb4d/download","source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Technical Report"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1899613237.pdf","grobid_xml":"https://content.openalex.org/works/W1899613237.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1489542082","https://openalex.org/W1576452626","https://openalex.org/W1603765807","https://openalex.org/W1745373831","https://openalex.org/W1987681749","https://openalex.org/W1991513691","https://openalex.org/W2004959510","https://openalex.org/W2008846452","https://openalex.org/W2019664122","https://openalex.org/W2027193513","https://openalex.org/W2034713309","https://openalex.org/W2066906122","https://openalex.org/W2068782949","https://openalex.org/W2078556239","https://openalex.org/W2092752818","https://openalex.org/W2105425553","https://openalex.org/W2119567691","https://openalex.org/W2131566641","https://openalex.org/W2162655762","https://openalex.org/W2168024904","https://openalex.org/W2229489617","https://openalex.org/W2334782222","https://openalex.org/W2400458653","https://openalex.org/W2949773717","https://openalex.org/W3169762705","https://openalex.org/W4245744559","https://openalex.org/W6684620542","https://openalex.org/W6689379321","https://openalex.org/W6796622633"],"related_works":["https://openalex.org/W1660242800","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2315999538","https://openalex.org/W2367222340","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"This":[0],"paper":[1],"considers":[2],"a":[3,19,25,61,91],"class":[4],"of":[5,45,53],"infinite":[6],"horizon":[7],"Markov":[8],"decision":[9,14],"processes":[10],"(MDPs)":[11],"with":[12],"multiple":[13],"makers,":[15],"called":[16],"agents,":[17],"and":[18,69,87],"general":[20],"joint":[21,105],"reward":[22,98],"structure,":[23],"but":[24],"special":[26],"decomposable":[27],"state/action":[28],"structure":[29],"such":[30,107],"that":[31,83,108],"each":[32,56,109],"individual":[33],"agent's":[34,110],"actions":[35,44],"affect":[36],"the":[37,43,51,96],"system's":[38],"state":[39,68],"transitions":[40],"independently":[41],"from":[42],"all":[46],"other":[47],"agents.":[48],"We":[49],"introduce":[50],"concept":[52],"\"localization,\"":[54],"where":[55],"agent":[57],"need":[58],"only":[59,115],"consider":[60],"\"local\"":[62],"MDP":[63],"defined":[64],"on":[65,73,114],"its":[66,116],"own":[67],"action":[70,111],"spaces.":[71],"Based":[72],"this":[74],"localization":[75],"concept,":[76],"we":[77],"propose":[78],"an":[79,103],"iterative":[80],"distributed":[81],"algorithm":[82],"emulates":[84],"gradient":[85],"ascent":[86],"which":[88],"converges":[89],"to":[90],"locally":[92],"optimal":[93],"solution":[94,101],"for":[95],"average":[97],"case.":[99],"The":[100],"is":[102,112],"\"autonomous\"":[104],"policy":[106],"based":[113],"local":[117],"state.":[118]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}