{"id":"https://openalex.org/W4315472209","doi":"https://doi.org/10.1109/cdc51059.2022.9992660","title":"Event-Based Communication in Distributed Q-Learning","display_name":"Event-Based Communication in Distributed Q-Learning","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4315472209","doi":"https://doi.org/10.1109/cdc51059.2022.9992660"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9992660","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc51059.2022.9992660","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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/A5057302113","display_name":"Daniel Jarne Ornia","orcid":"https://orcid.org/0000-0001-5949-8761"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Daniel Jarne Ornia","raw_affiliation_strings":["Delft University of Technology,Delft Centre for Systems and Control,Delft,The Netherlands","Delft Centre for Systems and Control, Delft University of Technology, Delft, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology,Delft Centre for Systems and Control,Delft,The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Centre for Systems and Control, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019241546","display_name":"Manuel Mazo","orcid":"https://orcid.org/0000-0002-5638-5283"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Manuel Mazo","raw_affiliation_strings":["Delft University of Technology,Delft Centre for Systems and Control,Delft,The Netherlands","Delft Centre for Systems and Control, Delft University of Technology, Delft, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology,Delft Centre for Systems and Control,Delft,The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Centre for Systems and Control, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5057302113"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":0.2162,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39154616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"8","issue":null,"first_page":"2379","last_page":"2386"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9972000122070312,"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/T13553","display_name":"Age of Information Optimization","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.768883228302002},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.762475848197937},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.616924524307251},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5605143904685974},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.49392396211624146},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4761602580547333},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.47491440176963806},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42937469482421875},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.42770087718963623},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3504672050476074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3423389792442322},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.2636427581310272},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12467893958091736}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.768883228302002},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.762475848197937},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.616924524307251},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5605143904685974},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.49392396211624146},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4761602580547333},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.47491440176963806},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42937469482421875},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42770087718963623},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3504672050476074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3423389792442322},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2636427581310272},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12467893958091736},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc51059.2022.9992660","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc51059.2022.9992660","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:tudelft.nl:uuid:1a7b9b77-2240-4e0c-b392-a951ab1d9451","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:1a7b9b77-2240-4e0c-b392-a951ab1d9451","pdf_url":null,"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,"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":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W56117469","https://openalex.org/W103885025","https://openalex.org/W1513468570","https://openalex.org/W1521003796","https://openalex.org/W1560074431","https://openalex.org/W1641379095","https://openalex.org/W1658008008","https://openalex.org/W1978518835","https://openalex.org/W2013629441","https://openalex.org/W2031788461","https://openalex.org/W2099618002","https://openalex.org/W2105695492","https://openalex.org/W2107544712","https://openalex.org/W2129387952","https://openalex.org/W2138965998","https://openalex.org/W2144817350","https://openalex.org/W2145339207","https://openalex.org/W2165131254","https://openalex.org/W2167183308","https://openalex.org/W2201581102","https://openalex.org/W2333874039","https://openalex.org/W2395575420","https://openalex.org/W2535838896","https://openalex.org/W2605628695","https://openalex.org/W2746553466","https://openalex.org/W2786928559","https://openalex.org/W2904435756","https://openalex.org/W2908064123","https://openalex.org/W2928090136","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2973229164","https://openalex.org/W2998299603","https://openalex.org/W3011272463","https://openalex.org/W3021654819","https://openalex.org/W3048802939","https://openalex.org/W3130631955","https://openalex.org/W4206354906","https://openalex.org/W4210475454","https://openalex.org/W4214717370","https://openalex.org/W4297687186","https://openalex.org/W4298300677","https://openalex.org/W4298857966","https://openalex.org/W4299802797","https://openalex.org/W6602332174","https://openalex.org/W6630520071","https://openalex.org/W6631137000","https://openalex.org/W6633472260","https://openalex.org/W6636881020","https://openalex.org/W6637967152","https://openalex.org/W6681423171","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6712181171","https://openalex.org/W6738796088","https://openalex.org/W6748554570","https://openalex.org/W6757082500","https://openalex.org/W6757184387","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2357975469","https://openalex.org/W2101748387","https://openalex.org/W3096874164","https://openalex.org/W4281812492","https://openalex.org/W3105579180","https://openalex.org/W2970347269","https://openalex.org/W2146763310","https://openalex.org/W3167472281","https://openalex.org/W4400868993"],"abstract_inverted_index":{"We":[0,23,104],"present":[1],"an":[2,40,85],"approach":[3],"to":[4,62,65,68,110,123,156],"reduce":[5],"the":[6,50,78,100,107,119,131,146],"communication":[7],"of":[8,28,74,102,130],"information":[9,67],"needed":[10],"on":[11,33,77,145],"a":[12,25,29,34,46,54,69,111,128],"Distributed":[13,30],"Q-Learning":[14,31],"system":[15,91],"inspired":[16],"by":[17],"Event":[18,86],"Triggered":[19],"Control":[20],"(ETC)":[21],"techniques.":[22],"consider":[24],"baseline":[26],"scenario":[27],"problem":[32],"Markov":[35],"Decision":[36],"Process":[37],"(MDP).":[38],"Following":[39],"event-based":[41,142],"approach,":[42],"N":[43],"agents":[44,120],"sharing":[45],"value":[47],"function":[48],"explore":[49],"MDP":[51],"and":[52,93,116,139,150],"compute":[53],"trajectory-dependent":[55],"triggering":[56],"signal":[57],"which":[58],"they":[59,152],"use":[60],"distributedly":[61],"decide":[63],"when":[64],"communicate":[66],"central":[70],"learner":[71],"in":[72],"charge":[73],"computing":[75],"updates":[76],"action-value":[79],"function.":[80],"These":[81],"decision":[82],"functions":[83],"form":[84],"Based":[87],"distributed":[88],"Q":[89],"learning":[90,147],"(EBd-Q),":[92],"we":[94,134],"derive":[95],"convergence":[96],"guarantees":[97],"resulting":[98],"from":[99],"reduction":[101],"communication.":[103],"then":[105],"apply":[106],"proposed":[108],"algorithm":[109],"cooperative":[112],"path":[113],"planning":[114],"problem,":[115],"show":[117],"how":[118,151],"are":[121],"able":[122],"learn":[124],"optimal":[125],"trajectories":[126],"communicating":[127],"fraction":[129],"information.":[132],"Additionally,":[133],"discuss":[135],"what":[136],"effects":[137],"(desired":[138],"undesired)":[140],"these":[141],"approaches":[143],"have":[144],"processes":[148],"studied,":[149],"can":[153],"be":[154],"applied":[155],"more":[157],"complex":[158],"multi-agent":[159],"systems.":[160]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2023-01-11T00:00:00"}