{"id":"https://openalex.org/W1985119984","doi":"https://doi.org/10.1109/adprl.2014.7010642","title":"Heuristics for multiagent reinforcement learning in decentralized decision problems","display_name":"Heuristics for multiagent reinforcement learning in decentralized decision problems","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1985119984","doi":"https://doi.org/10.1109/adprl.2014.7010642","mag":"1985119984"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2014.7010642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","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/A5048701748","display_name":"Martin Allen","orcid":null},"institutions":[{"id":"https://openalex.org/I4657992","display_name":"University of Wisconsin\u2013La Crosse","ror":"https://ror.org/00x8ccz20","country_code":"US","type":"education","lineage":["https://openalex.org/I4657992"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Martin W. Allen","raw_affiliation_strings":["Computer Science Department, University of Wisconsin-La Crosse, La Crosse, Wisconsin","Computer Science Department University of Wisconsin-La Crosse La Crosse, Wisconsin"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Wisconsin-La Crosse, La Crosse, Wisconsin","institution_ids":["https://openalex.org/I4657992"]},{"raw_affiliation_string":"Computer Science Department University of Wisconsin-La Crosse La Crosse, Wisconsin","institution_ids":["https://openalex.org/I4657992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041724634","display_name":"David F. Hahn","orcid":"https://orcid.org/0000-0003-2830-6880"},"institutions":[{"id":"https://openalex.org/I4657992","display_name":"University of Wisconsin\u2013La Crosse","ror":"https://ror.org/00x8ccz20","country_code":"US","type":"education","lineage":["https://openalex.org/I4657992"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Hahn","raw_affiliation_strings":["Computer Science Department, University of Wisconsin-La Crosse, La Crosse, Wisconsin","Computer Science Department University of Wisconsin-La Crosse La Crosse, Wisconsin"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Wisconsin-La Crosse, La Crosse, Wisconsin","institution_ids":["https://openalex.org/I4657992"]},{"raw_affiliation_string":"Computer Science Department University of Wisconsin-La Crosse La Crosse, Wisconsin","institution_ids":["https://openalex.org/I4657992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009502783","display_name":"Douglas C. MacFarland","orcid":null},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas C. MacFarland","raw_affiliation_strings":["Computer Science Department, Worcester Polytechnic Institute, Worcester, Massachusetts","Computer Science Department, Worcester Polytechnic Institute, Worcester, Massachusetts;"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Worcester Polytechnic Institute, Worcester, Massachusetts","institution_ids":["https://openalex.org/I107077323"]},{"raw_affiliation_string":"Computer Science Department, Worcester Polytechnic Institute, Worcester, Massachusetts;","institution_ids":["https://openalex.org/I107077323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048701748"],"corresponding_institution_ids":["https://openalex.org/I4657992"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0599859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T11182","display_name":"Auction Theory and Applications","score":0.982699990272522,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.9819999933242798,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8629347085952759},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.806977391242981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8009415864944458},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.7729368209838867},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7620120048522949},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6490126848220825},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6137338280677795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6002405285835266},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4673614501953125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4336884319782257},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43168479204177856},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.35978955030441284},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.2277488112449646},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.13693323731422424},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10259222984313965}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8629347085952759},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.806977391242981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8009415864944458},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.7729368209838867},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7620120048522949},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6490126848220825},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6137338280677795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6002405285835266},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4673614501953125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4336884319782257},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43168479204177856},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.35978955030441284},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2277488112449646},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.13693323731422424},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10259222984313965},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/adprl.2014.7010642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1557517019","https://openalex.org/W1560489415","https://openalex.org/W1566869837","https://openalex.org/W1575232410","https://openalex.org/W1579579904","https://openalex.org/W1805286982","https://openalex.org/W1908253641","https://openalex.org/W1965555277","https://openalex.org/W1977070092","https://openalex.org/W2006681603","https://openalex.org/W2029280655","https://openalex.org/W2085366587","https://openalex.org/W2088956500","https://openalex.org/W2099618002","https://openalex.org/W2104602264","https://openalex.org/W2117117839","https://openalex.org/W2119567691","https://openalex.org/W2122905566","https://openalex.org/W2146950091","https://openalex.org/W2168359464","https://openalex.org/W2334782222","https://openalex.org/W2952328111","https://openalex.org/W4231746564","https://openalex.org/W6633466248","https://openalex.org/W6634147214","https://openalex.org/W6634317047","https://openalex.org/W6634752865","https://openalex.org/W6638218530","https://openalex.org/W6640044251","https://openalex.org/W6672070530","https://openalex.org/W6675811377","https://openalex.org/W6677134410","https://openalex.org/W6678387239"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W3096874164","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W2937181779","https://openalex.org/W2386410636"],"abstract_inverted_index":{"Decentralized":[0],"partially":[1],"observable":[2],"Markov":[3],"decision":[4],"processes":[5],"(Dec-POMDPs)":[6],"model":[7],"cooperative":[8],"multiagent":[9],"scenarios,":[10],"providing":[11],"a":[12,50,102,115],"powerful":[13],"general":[14],"framework":[15],"for":[16,24,35,60],"team-based":[17],"artificial":[18],"intelligence.":[19],"While":[20],"optimal":[21],"algorithms":[22],"exist":[23],"Dec-POMDPs,":[25],"theoretical":[26],"and":[27],"empirical":[28],"results":[29,72],"demonstrate":[30],"that":[31,68,90,106],"they":[32],"are":[33],"impractical":[34],"many":[36],"problems":[37],"of":[38,45,73,86],"real":[39],"interest.":[40],"We":[41,77],"examine":[42],"the":[43,84,87,92,121],"use":[44],"reinforcement":[46],"learning":[47,93,111,122],"(RL)":[48],"as":[49],"means":[51],"to":[52,95],"generate":[53],"adequate,":[54],"if":[55],"not":[56],"optimal,":[57],"joint":[58,75],"policies":[59],"Dec-POMDPs.":[61],"It":[62],"is":[63],"easily":[64],"demonstrated":[65],"(and":[66],"expected)":[67],"single-agent":[69],"RL":[70],"produces":[71],"little":[74],"utility.":[76],"therefore":[78],"investigate":[79],"heuristic":[80,117],"methods,":[81],"based":[82],"upon":[83],"dynamics":[85],"Dec-POMDP":[88],"formulation,":[89],"bias":[91],"process":[94,123],"produce":[96],"coordinated":[97],"action.":[98],"Empirical":[99],"tests":[100],"on":[101],"benchmark":[103],"problem":[104],"show":[105],"these":[107],"heuristics":[108],"significantly":[109],"enhance":[110],"performance,":[112],"even":[113],"out-performing":[114],"hand-crafted":[116],"in":[118],"cases":[119],"where":[120],"converges":[124],"quickly.":[125]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}