乐胖代购免代理版

{"id":"https://openalex.org/W2788249729","doi":"https://doi.org/10.1609/aaai.v32i1.12096","title":"Planning and Learning for Decentralized MDPs With Event Driven Rewards","display_name":"Planning and Learning for Decentralized MDPs With Event Driven Rewards","publication_year":2018,"publication_date":"2018-04-26","ids":{"openalex":"https://openalex.org/W2788249729","doi":"https://doi.org/10.1609/aaai.v32i1.12096","mag":"2788249729"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v32i1.12096","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/12096/11955","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/12096/11955","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101214183","display_name":"Tarun Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tarun Gupta","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101059249","display_name":"Akshat Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"funder","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Akshat Kumar","raw_affiliation_strings":["Singapore Management University"],"affiliations":[{"raw_affiliation_string":"Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000689728","display_name":"Praveen Paruchuri","orcid":"https://orcid.org/0000-0001-8071-5409"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Praveen Paruchuri","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad","institution_ids":["https://openalex.org/I64189192"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.043,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":9,"citation_normalized_percentile":{"value":0.760725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":84,"max":85},"biblio":{"volume":"32","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9963,"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"}},"topics":[{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9963,"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"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9957,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9926,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77113926},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7100993},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6353773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6118527},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.60656196},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.57348573},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.52725923},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5256751},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46354172},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.45511088},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v32i1.12096","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/12096/11955","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v32i1.12096","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/12096/11955","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.6}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":44,"referenced_works":["https://openalex.org/W1182044309","https://openalex.org/W1511497483","https://openalex.org/W1588304026","https://openalex.org/W1646152356","https://openalex.org/W1749432972","https://openalex.org/W176675923","https://openalex.org/W1769870091","https://openalex.org/W181022050","https://openalex.org/W1852310822","https://openalex.org/W1936503582","https://openalex.org/W1970101292","https://openalex.org/W1972774725","https://openalex.org/W2019738489","https://openalex.org/W2026315107","https://openalex.org/W2049633694","https://openalex.org/W2087992130","https://openalex.org/W2088956500","https://openalex.org/W2102764452","https://openalex.org/W2119567691","https://openalex.org/W2119717200","https://openalex.org/W2131648741","https://openalex.org/W2142505627","https://openalex.org/W2143867639","https://openalex.org/W2153821047","https://openalex.org/W2155027007","https://openalex.org/W2166515056","https://openalex.org/W2277038666","https://openalex.org/W2290743114","https://openalex.org/W2295617766","https://openalex.org/W2296626015","https://openalex.org/W2545853213","https://openalex.org/W2548322271","https://openalex.org/W2575718630","https://openalex.org/W2604704722","https://openalex.org/W2617547828","https://openalex.org/W2952726221","https://openalex.org/W2962938168","https://openalex.org/W2963497400","https://openalex.org/W2964134875","https://openalex.org/W2964155655","https://openalex.org/W3023084835","https://openalex.org/W4230563027","https://openalex.org/W4232967792","https://openalex.org/W4293676776"],"related_works":["https://openalex.org/W4380318855","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W3049728571","https://openalex.org/W2586732548","https://openalex.org/W2389214306","https://openalex.org/W2163814182","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2024136090"],"abstract_inverted_index":{"Decentralized":[0],"(PO)MDPs":[1],"provide":[2],"a":[3,33,103,133,145],"rigorous":[4],"framework":[5],"for":[6,84,102,121],"sequential":[7],"multiagent":[8,113,136],"decision":[9],"making":[10],"under":[11],"uncertainty.":[12],"However,":[13],"their":[14,46],"high":[15],"computational":[16],"complexity":[17],"limits":[18],"the":[19,57,65,72],"practical":[20],"impact.":[21],"To":[22],"address":[23],"scalability":[24],"and":[25,51,126],"real-world":[26,135],"impact,":[27],"we":[28,77],"focus":[29],"on":[30,45],"settings":[31],"where":[32,150],"large":[34,104,134],"number":[35,105],"of":[36,49,59,106,142],"agents":[37,143],"primarily":[38],"interact":[39],"through":[40],"complex":[41],"joint-rewards":[42],"that":[43,64,95,117],"depend":[44],"entire":[47],"histories":[48],"states":[50],"actions.":[52],"Such":[53],"history-based":[54],"rewards":[55],"encapsulate":[56],"notion":[58],"events":[60],"or":[61],"tasks":[62],"such":[63,85],"team":[66],"reward":[67],"is":[68,74],"given":[69],"only":[70],"when":[71],"joint-task":[73],"completed.":[75],"Algorithmically,":[76],"contribute---1)":[78],"A":[79,90,109],"nonlinear":[80],"programming":[81],"(NLP)":[82],"formulation":[83],"event-based":[86],"planning":[87],"model;":[88],"2)":[89],"probabilistic":[91],"inference":[92,125],"based":[93,112],"approach":[94,116],"scales":[96,118],"much":[97],"better":[98],"than":[99],"NLP":[100],"solvers":[101],"agents;":[107],"3)":[108],"policy":[110],"gradient":[111],"reinforcement":[114],"learning":[115],"well":[119],"even":[120],"exponential":[122],"state-spaces.":[123],"Our":[124],"RL-based":[127],"advances":[128],"enable":[129],"us":[130],"to":[131,154],"solve":[132],"coverage":[137],"problem":[138],"modeling":[139],"schedule":[140],"coordination":[141],"in":[144],"real":[146],"urban":[147],"subway":[148],"network":[149],"other":[151],"approaches":[152],"fail":[153],"scale.":[155]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2788249729","counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-03-15T20:24:21.053094","created_date":"2018-03-06"}