{"id":"https://openalex.org/W1998727078","doi":"https://doi.org/10.1145/2668130","title":"Reinforcement Learning of Informed Initial Policies for Decentralized Planning","display_name":"Reinforcement Learning of Informed Initial Policies for Decentralized Planning","publication_year":2014,"publication_date":"2014-12-08","ids":{"openalex":"https://openalex.org/W1998727078","doi":"https://doi.org/10.1145/2668130","mag":"1998727078"},"language":"en","primary_location":{"id":"doi:10.1145/2668130","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2668130","pdf_url":null,"source":{"id":"https://openalex.org/S16632050","display_name":"ACM Transactions on Autonomous and Adaptive Systems","issn_l":"1556-4665","issn":["1556-4665","1556-4703"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Autonomous and Adaptive Systems","raw_type":"journal-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/A5048144212","display_name":"Landon Kraemer","orcid":null},"institutions":[{"id":"https://openalex.org/I44854399","display_name":"University of Southern Mississippi","ror":"https://ror.org/0270vfa57","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I44854399"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Landon Kraemer","raw_affiliation_strings":["University of Southern Mississippi, Hattiesburg, Mississippi","University of Southern Mississippi, Hattiesburg, Mississippi#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Southern Mississippi, Hattiesburg, Mississippi","institution_ids":["https://openalex.org/I44854399"]},{"raw_affiliation_string":"University of Southern Mississippi, Hattiesburg, Mississippi#TAB#","institution_ids":["https://openalex.org/I44854399"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025954824","display_name":"Bikramjit Banerjee","orcid":"https://orcid.org/0000-0001-7999-0307"},"institutions":[{"id":"https://openalex.org/I44854399","display_name":"University of Southern Mississippi","ror":"https://ror.org/0270vfa57","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I44854399"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bikramjit Banerjee","raw_affiliation_strings":["University of Southern Mississippi, Hattiesburg, Mississippi","University of Southern Mississippi, Hattiesburg, Mississippi#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Southern Mississippi, Hattiesburg, Mississippi","institution_ids":["https://openalex.org/I44854399"]},{"raw_affiliation_string":"University of Southern Mississippi, Hattiesburg, Mississippi#TAB#","institution_ids":["https://openalex.org/I44854399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048144212"],"corresponding_institution_ids":["https://openalex.org/I44854399"],"apc_list":null,"apc_paid":null,"fwci":0.422,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73841039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"9","issue":"4","first_page":"1","last_page":"32"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9435999989509583,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9368000030517578,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9071693420410156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8696585893630981},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7014998197555542},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6861491203308105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5059720873832703},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.45309051871299744},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.43810027837753296},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.3688564896583557},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3210628032684326},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.26912373304367065},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.15130692720413208}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9071693420410156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8696585893630981},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7014998197555542},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6861491203308105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5059720873832703},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.45309051871299744},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.43810027837753296},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3688564896583557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3210628032684326},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.26912373304367065},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.15130692720413208},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2668130","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2668130","pdf_url":null,"source":{"id":"https://openalex.org/S16632050","display_name":"ACM Transactions on Autonomous and Adaptive Systems","issn_l":"1556-4665","issn":["1556-4665","1556-4703"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Autonomous and Adaptive Systems","raw_type":"journal-article"},{"id":"pmh:oai:aquila.usm.edu:fac_pubs-16630","is_oa":false,"landing_page_url":"https://aquila.usm.edu/fac_pubs/15312","pdf_url":null,"source":{"id":"https://openalex.org/S4306402529","display_name":"Aquila Digital Community (University of Southern Mississippi)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I44854399","host_organization_name":"University of Southern Mississippi","host_organization_lineage":["https://openalex.org/I44854399"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7200000286102295}],"awards":[{"id":"https://openalex.org/G1017873567","display_name":null,"funder_award_id":"W911NF-11-1-0124","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W85998123","https://openalex.org/W156814138","https://openalex.org/W1503287497","https://openalex.org/W1515851193","https://openalex.org/W1560489415","https://openalex.org/W1563317173","https://openalex.org/W1580557482","https://openalex.org/W1583380718","https://openalex.org/W1640774615","https://openalex.org/W1657674574","https://openalex.org/W2088956500","https://openalex.org/W2104602264","https://openalex.org/W2105703084","https://openalex.org/W2108005621","https://openalex.org/W2128814508","https://openalex.org/W2131747355","https://openalex.org/W2149202145","https://openalex.org/W2168359464","https://openalex.org/W2192622472","https://openalex.org/W2294663333","https://openalex.org/W2312609093","https://openalex.org/W2400387077","https://openalex.org/W2404646363","https://openalex.org/W2591957553","https://openalex.org/W2608239929","https://openalex.org/W2699476589","https://openalex.org/W2739348915","https://openalex.org/W2791379569","https://openalex.org/W3148958427"],"related_works":["https://openalex.org/W3208638985","https://openalex.org/W2183018497","https://openalex.org/W3118263362","https://openalex.org/W1662842982","https://openalex.org/W4310829038","https://openalex.org/W2963561234","https://openalex.org/W3162151154","https://openalex.org/W2809005670","https://openalex.org/W3092978326","https://openalex.org/W2284610481"],"abstract_inverted_index":{"Decentralized":[0],"partially":[1],"observable":[2],"Markov":[3],"decision":[4],"processes":[5],"(Dec-POMDPs)":[6],"offer":[7],"a":[8,83,91,111],"formal":[9],"model":[10,36],"for":[11,90],"planning":[12],"in":[13,105,121],"cooperative":[14],"multiagent":[15],"systems":[16],"where":[17,51],"agents":[18,52],"operate":[19],"with":[20,131],"noisy":[21],"sensors":[22],"and":[23,35],"actuators,":[24],"as":[25,27,138],"well":[26],"local":[28],"information.":[29],"Prevalent":[30],"solution":[31],"techniques":[32],"are":[33],"centralized":[34],"based\u2014limitations":[37],"that":[38,86,98],"we":[39],"address":[40],"by":[41],"distributed":[42],"reinforcement":[43],"learning":[44,68,129],"(RL).":[45],"We":[46,73,95],"particularly":[47],"favor":[48],"alternate":[49,67,126],"learning,":[50],"alternately":[53],"learn":[54],"best":[55,127],"responses":[56],"to":[57,62,78,113],"each":[58],"other,":[59],"which":[60],"appears":[61],"outperform":[63],"concurrent":[64],"RL.":[65],"However,":[66],"requires":[69],"an":[70,115],"initial":[71,81],"policy.":[72],"propose":[74],"two":[75],"principled":[76],"approaches":[77],"generating":[79],"informed":[80],"policies:":[82],"naive":[84],"approach":[85,101],"lays":[87],"the":[88,99],"foundation":[89],"more":[92],"sophisticated":[93],"approach.":[94],"empirically":[96],"demonstrate":[97],"refined":[100],"produces":[102],"near-optimal":[103],"solutions":[104],"many":[106],"challenging":[107],"benchmark":[108],"settings,":[109],"staking":[110],"claim":[112],"being":[114],"efficient":[116],"(and":[117],"realistic)":[118],"approximate":[119],"solver":[120],"its":[122],"own":[123],"right.":[124],"Furthermore,":[125],"response":[128],"seeded":[130],"such":[132],"policies":[133,137],"quickly":[134],"learns":[135],"high-quality":[136],"well.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}