{"id":"https://openalex.org/W1505385280","doi":null,"title":"Reinforcement Learning in Distributed Domains: Beyond Team Games","display_name":"Reinforcement Learning in Distributed Domains: Beyond Team Games","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W1505385280","mag":"1505385280"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.380.5402","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.380.5402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.engr.oregonstate.edu/~ktumer/publications/files/tumer-wolpert_ijcai01.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5073514351","display_name":"David H. Wolpert","orcid":"https://orcid.org/0000-0003-3105-2869","observed_orcids":["https://orcid.org/0000-0003-3105-2869","https://orcid.org/0000-0001-5114-8361"]},"institutions":[{"id":"https://openalex.org/I1280536761","display_name":"Ames Research Center","ror":"https://ror.org/02acart68","country_code":"US","type":"facility","lineage":["https://openalex.org/I1280536761","https://openalex.org/I4210124779"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David H. Wolpert","raw_affiliation_strings":["NASA Ames Research Center Moffett Field CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NASA Ames Research Center Moffett Field CA","institution_ids":["https://openalex.org/I1280536761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056504335","display_name":"Joseph Sill","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joseph Sill","raw_affiliation_strings":["Ripfire, Inc., San Fransisco, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ripfire, Inc., San Fransisco, CA#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084748531","display_name":"Kagan Tumer","orcid":"https://orcid.org/0009-0007-3809-7257","observed_orcids":["https://orcid.org/0009-0007-3809-7257"]},"institutions":[{"id":"https://openalex.org/I1280536761","display_name":"Ames Research Center","ror":"https://ror.org/02acart68","country_code":"US","type":"facility","lineage":["https://openalex.org/I1280536761","https://openalex.org/I4210124779"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kagan Tumer","raw_affiliation_strings":["NASA Ames Research Center Moffett Field CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NASA Ames Research Center Moffett Field CA","institution_ids":["https://openalex.org/I1280536761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4093,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.89595162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9761000275611877,"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":0.9761000275611877,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.007899999618530273,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.0027000000700354576,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/distributed-reinforcement-learning","display_name":"distributed reinforcement learning","score":0.9200000166893005},{"id":"https://openalex.org/keywords/team-games","display_name":"team games","score":0.8640000224113464},{"id":"https://openalex.org/keywords/simulated-annealing","display_name":"simulated annealing","score":0.9950000047683716},{"id":"https://openalex.org/keywords/search-algorithms","display_name":"search algorithms","score":0.5789999961853027},{"id":"https://openalex.org/keywords/route-optimization","display_name":"route optimization","score":0.49300000071525574}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8740003108978271},{"id":"https://openalex.org/C135450995","wikidata":"https://www.wikidata.org/wiki/Q820272","display_name":"Hill climbing","level":2,"score":0.8580885529518127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7488415837287903},{"id":"https://openalex.org/C95038775","wikidata":"https://www.wikidata.org/wiki/Q22857","display_name":"Climbing","level":2,"score":0.5280631184577942},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5045892000198364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5026166439056396},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3998510241508484},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11388123035430908},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10054081678390503},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.380.5402","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.380.5402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.engr.oregonstate.edu/~ktumer/publications/files/tumer-wolpert_ijcai01.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.7.3546","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.7.3546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ic.arc.nasa.gov/~kagan/pubs/ijcai_2001_const.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1483256023","https://openalex.org/W1513468570","https://openalex.org/W1515851193","https://openalex.org/W1525019474","https://openalex.org/W1554015367","https://openalex.org/W1562346140","https://openalex.org/W1585546214","https://openalex.org/W1982239148","https://openalex.org/W1982647060","https://openalex.org/W1985093013","https://openalex.org/W2008437221","https://openalex.org/W2024060531","https://openalex.org/W2032431794","https://openalex.org/W2038303746","https://openalex.org/W2053616263","https://openalex.org/W2063317962","https://openalex.org/W2096037858","https://openalex.org/W2104602264","https://openalex.org/W2107726111","https://openalex.org/W2117341272","https://openalex.org/W2118899043","https://openalex.org/W2121863487","https://openalex.org/W2126306851","https://openalex.org/W2150795121","https://openalex.org/W2169528473","https://openalex.org/W2171234133","https://openalex.org/W2227557434","https://openalex.org/W2613173048"],"related_works":["https://openalex.org/W7099406384","https://openalex.org/W7097276391","https://openalex.org/W3127151746","https://openalex.org/W2550232246","https://openalex.org/W1862928768","https://openalex.org/W2113700172","https://openalex.org/W3011272463","https://openalex.org/W7124239994","https://openalex.org/W3217297494","https://openalex.org/W2015321987"],"abstract_inverted_index":{"Using":[0],"a":[1,6,45,56,110,167,193],"distributed":[2,57,73,82,143,179,206],"algorithm":[3,47,74,83,165,181,196,208],"rather":[4],"than":[5],"centralized":[7],"one":[8],"can":[9],"be":[10,145],"extremely":[11],"beneficial":[12],"in":[13,55,98,166,213],"large":[14],"search":[15,30,46,191,195],"problems.":[16],"In":[17,40],"addition,":[18],"the":[19,61,81,86,90,99,103,120,139,142,146,153,156,163],"incorporation":[20],"of":[21,89,101,105,112,122,128,141,148,155],"machine":[22],"learning":[23],"techniques":[24],"like":[25],"Reinforcement":[26],"Learning":[27],"(RL)":[28],"into":[29,152],"algorithms":[31,97,125],"has":[32],"often":[33],"been":[34],"found":[35],"to":[36,84,182],"improve":[37],"their":[38],"performance.":[39,172],"this":[41,117,136],"article":[42],"we":[43,118],"investigate":[44,94],"that":[48,161,169,175,189,197,205],"combines":[49],"these":[50,96,124],"properties":[51],"by":[52,79,137],"employing":[53],"RL":[54,180,207],"manner,":[58],"essentially":[59],"using":[60,80,95,176],"team":[62],"game":[63],"approach.":[64],"We":[65,93,173],"then":[66],"present":[67],"bi-utility":[68,190],"search,":[69],"which":[70],"interleaves":[71],"our":[72,177,214],"with":[75],"(centralized)":[76,210],"simulated":[77,91,211],"annealing,":[78],"guide":[85],"exploration":[87],"step":[88],"annealing.":[92],"domain":[100],"minimizing":[102],"loss":[104],"importance-weighted":[106],"communication":[107,113],"data":[108],"traversing":[109],"constellations":[111],"satellites.":[114],"To":[115],"do":[116,135],"introduce":[119],"idea":[121],"running":[123],"\"on":[126],"top\"":[127],"an":[129],"underlying,":[130],"learning-free":[131],"routing":[132,158,164],"algorithm.":[133],"They":[134],"having":[138],"actions":[140],"learners":[144],"introduction":[147],"virtual":[149],"\"ghost\"":[150],"traffic":[151,160,185],"decision-making":[154],"underlying":[157],"algorithm,":[159],"\"misleads\"":[162],"way":[168],"actually":[170],"improves":[171,186],"find":[174],"original":[178],"set":[183],"ghost":[184],"performance,":[187],"and":[188,209],"---":[192,201],"semi-distributed":[194],"is":[198],"widely":[199],"applicable":[200],"substantially":[202],"outperforms":[203],"both":[204],"annealing":[212],"problem":[215],"domain.":[216]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}