{"id":"https://openalex.org/W80106572","doi":null,"title":"Multi-Agent Actor-Critic Reinforcement Learning for Cooperative Tasks","display_name":"Multi-Agent Actor-Critic Reinforcement Learning for Cooperative Tasks","publication_year":2014,"publication_date":"2014-08-04","ids":{"openalex":"https://openalex.org/W80106572","mag":"80106572"},"language":"en","primary_location":{"id":"pmh:oai:tudelft.nl:uuid:033c4238-62e8-4ef7-b43d-b43f3b97856f","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:033c4238-62e8-4ef7-b43d-b43f3b97856f","pdf_url":"http://resolver.tudelft.nl/uuid:033c4238-62e8-4ef7-b43d-b43f3b97856f","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://resolver.tudelft.nl/uuid:033c4238-62e8-4ef7-b43d-b43f3b97856f","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038883044","display_name":"Ya\u011fiz E. Bayiz","orcid":"https://orcid.org/0000-0001-9689-7606","observed_orcids":["https://orcid.org/0000-0001-9689-7606"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ya\u011fiz E. Bayiz","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9689-7606","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5038883044"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":1.0,"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":1.0,"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":0.0,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.0,"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/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.9520000219345093},{"id":"https://openalex.org/keywords/actor-critic","display_name":"actor-critic","score":0.8939999938011169},{"id":"https://openalex.org/keywords/cooperative-multi-agent-systems","display_name":"cooperative multi-agent systems","score":0.972000002861023},{"id":"https://openalex.org/keywords/independent-learners","display_name":"independent learners","score":0.7599999904632568},{"id":"https://openalex.org/keywords/two-link-manipulator","display_name":"two-link manipulator","score":0.8460000157356262},{"id":"https://openalex.org/keywords/distributed-control","display_name":"distributed control","score":0.7149999737739563},{"id":"https://openalex.org/keywords/continuous-action-spaces","display_name":"continuous action spaces","score":0.4449999928474426}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8678250908851624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6463087201118469},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5986772775650024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.52149498462677},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4413437843322754},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.42232757806777954},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.412229061126709},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3822067379951477},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17516544461250305},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:tudelft.nl:uuid:033c4238-62e8-4ef7-b43d-b43f3b97856f","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:033c4238-62e8-4ef7-b43d-b43f3b97856f","pdf_url":"http://resolver.tudelft.nl/uuid:033c4238-62e8-4ef7-b43d-b43f3b97856f","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"},{"id":"mag:80106572","doi":null,"is_oa":false,"landing_page_url":"http://repository.tudelft.nl/islandora/object/uuid:033c4238-62e8-4ef7-b43d-b43f3b97856f/?collection=research","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:tudelft.nl:uuid:033c4238-62e8-4ef7-b43d-b43f3b97856f","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:033c4238-62e8-4ef7-b43d-b43f3b97856f","pdf_url":"http://resolver.tudelft.nl/uuid:033c4238-62e8-4ef7-b43d-b43f3b97856f","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W80106572.pdf","grobid_xml":"https://content.openalex.org/works/W80106572.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W137071854","https://openalex.org/W153087758","https://openalex.org/W1484740474","https://openalex.org/W1553320709","https://openalex.org/W1560074431","https://openalex.org/W1576452626","https://openalex.org/W1579184372","https://openalex.org/W1583833196","https://openalex.org/W1594783240","https://openalex.org/W1607654861","https://openalex.org/W1639167632","https://openalex.org/W1641379095","https://openalex.org/W1873332500","https://openalex.org/W1966086707","https://openalex.org/W1979638690","https://openalex.org/W2009303086","https://openalex.org/W2046376809","https://openalex.org/W2046765929","https://openalex.org/W2050124350","https://openalex.org/W2088956500","https://openalex.org/W2094387729","https://openalex.org/W2096145798","https://openalex.org/W2099618002","https://openalex.org/W2104144149","https://openalex.org/W2104602264","https://openalex.org/W2108449787","https://openalex.org/W2113913482","https://openalex.org/W2117341272","https://openalex.org/W2118318536","https://openalex.org/W2119567691","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2139053308","https://openalex.org/W2143490508","https://openalex.org/W2147492008","https://openalex.org/W2155027007","https://openalex.org/W2165150801","https://openalex.org/W2167417157","https://openalex.org/W2169209873","https://openalex.org/W2341171179","https://openalex.org/W2912889105","https://openalex.org/W6884722281"],"related_works":["https://openalex.org/W4416743863","https://openalex.org/W4394843610","https://openalex.org/W3205579016","https://openalex.org/W4234146654","https://openalex.org/W3036329728","https://openalex.org/W7163654165","https://openalex.org/W2913326990","https://openalex.org/W3128102899","https://openalex.org/W7029483213","https://openalex.org/W4385484866"],"abstract_inverted_index":{"For":[0],"single-agent":[1,60],"problems,":[2],"Reinforcement":[3,167],"Learning":[4,168,231],"(RL)":[5],"algorithms":[6,44,253,273],"proved":[7],"to":[8,28,34,58,91,97,106,116,150,165,195,200,203,216,237,295],"be":[9,29],"useful":[10],"learning":[11,266,286],"optimal":[12],"control":[13,61,122,133,146,219],"laws":[14],"for":[15,170],"nonlinear":[16],"dynamic":[17],"systems":[18],"without":[19],"relying":[20],"on":[21,36,256],"a":[22,77,93,102,140,152,157,217,222],"mathematical":[23],"model":[24],"of":[25,79,85,114,135,160,191,207,224,239,268,285],"the":[26,132,177,205,213,240,264,269,279,283,289,296],"system":[27],"controlled.":[30],"With":[31],"their":[32],"ability":[33],"work":[35],"continuous":[37],"action":[38],"and":[39,74,110,123,173,211,248,288],"state":[40],"spaces,":[41],"actor-critic":[42,53,178,197],"RL":[43,198],"are":[45,254],"especially":[46],"advantageous":[47],"in":[48,127,145,180,187],"that":[49],"manner.":[50],"So":[51,155],"far,":[52,156],"methods":[54,179,199,215],"have":[55,139,183],"been":[56,163,185],"applied":[57],"several":[59],"problems":[62,147],"often":[63],"with":[64],"impressive":[65],"results.":[66],"A":[67],"Multi-Agent":[68,166],"System":[69],"(MAS)":[70],"distributes":[71],"computational":[72],"resources":[73],"capabilities":[75],"across":[76],"network":[78],"interconnected":[80],"agents.":[81],"The":[82,189,251,260],"main":[83],"advantage":[84],"using":[86],"such":[87,118,228],"an":[88],"approach":[89],"is":[90,101,194,235,274,292],"distribute":[92],"globally":[94],"complex":[95],"problem":[96,220],"simpler":[98],"sub-problems,":[99],"which":[100],"more":[103],"natural":[104],"way":[105],"address":[107],"source":[108],"allocation":[109],"team":[111],"planning.":[112],"Application":[113],"MAS":[115,138,202],"domains,":[117],"as":[119,221],"robotics,":[120],"distributed":[121],"telecommunications,":[124],"gained":[125],"popularity":[126],"last":[128],"two":[129,209,238],"decades.":[130],"From":[131],"point":[134],"view,":[136],"cooperative":[137,172,201],"special":[141],"importance":[142],"since":[143],"agents":[144],"frequently":[148],"seek":[149],"achieve":[151,227],"joint":[153],"goal.":[154],"significant":[158],"amount":[159],"research":[161],"has":[162],"dedicated":[164],"(MARL)":[169],"both":[171],"non-cooperative":[174],"tasks.":[175],"Yet,":[176],"MARL":[181],"context":[182],"not":[184],"examined":[186],"detailed.":[188],"aim":[190],"this":[192],"project":[193],"implement":[196],"combine":[204],"advantages":[206],"these":[208],"approaches":[210],"apply":[212],"resulting":[214,252],"real-life":[218],"proof":[223],"concept.":[225],"To":[226],"task":[229],"Model":[230],"Actor-Critic":[232],"(MLAC)":[233],"algorithm":[234],"extended":[236],"Independent":[241],"Learners":[242],"(IL)":[243],"based":[244],"methods:":[245],"optimistic":[246],"learners":[247],"lenient":[249],"learners.":[250],"tested":[255],"2-link":[257],"manipulator":[258],"problem.":[259],"results":[261],"indicate":[262],"that,":[263],"initial":[265],"speed":[267],"proposed":[270],"multi-agent":[271],"MLAC":[272,281],"similar":[275],"or":[276],"faster":[277],"than":[278],"centralized":[280,297],"at":[282],"start":[284],"experiments,":[287],"end":[290],"performance":[291],"acceptable":[293],"compared":[294],"MLAC.":[298]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-08T09:06:37.294493","created_date":"2016-06-24T00:00:00"}