{"id":"https://openalex.org/W3170432462","doi":"https://doi.org/10.1109/ieeeconf51394.2020.9443572","title":"Distributed Hybrid Kalman Temporal Differences for Reinforcement Learning","display_name":"Distributed Hybrid Kalman Temporal Differences for Reinforcement Learning","publication_year":2020,"publication_date":"2020-11-01","ids":{"openalex":"https://openalex.org/W3170432462","doi":"https://doi.org/10.1109/ieeeconf51394.2020.9443572","mag":"3170432462"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf51394.2020.9443572","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf51394.2020.9443572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 54th Asilomar Conference on Signals, Systems, and Computers","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/A5007482562","display_name":"Mohammad Salimibeni","orcid":"https://orcid.org/0000-0003-0382-0007"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Mohammad Salimibeni","raw_affiliation_strings":["Concordia University,Concordia Institute for Information Systems Engineering,Montreal,QC,Canada","Concordia Institute for Information Systems Engineering, Concordia University, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Concordia University,Concordia Institute for Information Systems Engineering,Montreal,QC,Canada","institution_ids":["https://openalex.org/I60158472"]},{"raw_affiliation_string":"Concordia Institute for Information Systems Engineering, Concordia University, Montreal, QC, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017386905","display_name":"Parvin Malekzadeh","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Parvin Malekzadeh","raw_affiliation_strings":["University of Toronto,Department of Electrical and Computer Engineering,Toronto,ON,Canada","Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto,Department of Electrical and Computer Engineering,Toronto,ON,Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058253407","display_name":"Arash Mohammadi","orcid":"https://orcid.org/0000-0003-1972-7923"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Arash Mohammadi","raw_affiliation_strings":["Concordia University,Concordia Institute for Information Systems Engineering,Montreal,QC,Canada","Concordia Institute for Information Systems Engineering, Concordia University, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Concordia University,Concordia Institute for Information Systems Engineering,Montreal,QC,Canada","institution_ids":["https://openalex.org/I60158472"]},{"raw_affiliation_string":"Concordia Institute for Information Systems Engineering, Concordia University, Montreal, QC, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059152392","display_name":"Konstantinos N. Plataniotis","orcid":"https://orcid.org/0000-0003-3647-5473"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Konstantinos N. Plataniotis","raw_affiliation_strings":["University of Toronto,Department of Electrical and Computer Engineering,Toronto,ON,Canada","Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto,Department of Electrical and Computer Engineering,Toronto,ON,Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007482562"],"corresponding_institution_ids":["https://openalex.org/I60158472"],"apc_list":null,"apc_paid":null,"fwci":0.3977,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70767635,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"579","last_page":"583"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9940999746322632,"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/T10524","display_name":"Traffic control and management","score":0.9904000163078308,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8460206985473633},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.764373779296875},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7178505659103394},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.6372761726379395},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4985527992248535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48077672719955444},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.473020076751709},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.468083918094635},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44755059480667114},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.42612358927726746},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3456052839756012},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33875057101249695},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3014761209487915},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1042516827583313}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8460206985473633},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.764373779296875},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7178505659103394},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.6372761726379395},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4985527992248535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48077672719955444},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.473020076751709},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.468083918094635},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44755059480667114},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.42612358927726746},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3456052839756012},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33875057101249695},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3014761209487915},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1042516827583313},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf51394.2020.9443572","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf51394.2020.9443572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 54th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W166862392","https://openalex.org/W1498369939","https://openalex.org/W1757796397","https://openalex.org/W1978294824","https://openalex.org/W1998172110","https://openalex.org/W1999912147","https://openalex.org/W2018500972","https://openalex.org/W2038128936","https://openalex.org/W2062541405","https://openalex.org/W2072931156","https://openalex.org/W2109102709","https://openalex.org/W2112032710","https://openalex.org/W2121138345","https://openalex.org/W2121863487","https://openalex.org/W2124776405","https://openalex.org/W2133733518","https://openalex.org/W2156064084","https://openalex.org/W2158796564","https://openalex.org/W2158984235","https://openalex.org/W2167144895","https://openalex.org/W2168342951","https://openalex.org/W2173248099","https://openalex.org/W2340447012","https://openalex.org/W2681546569","https://openalex.org/W2735133106","https://openalex.org/W2738778707","https://openalex.org/W2774907159","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2858816864","https://openalex.org/W2963864421","https://openalex.org/W2966477667","https://openalex.org/W2969428710","https://openalex.org/W2972533062","https://openalex.org/W2972792546","https://openalex.org/W2977915324","https://openalex.org/W2998165854","https://openalex.org/W3000501873","https://openalex.org/W3006486026","https://openalex.org/W3041107988","https://openalex.org/W4214717370","https://openalex.org/W4298857966","https://openalex.org/W6629718364","https://openalex.org/W6637967152","https://openalex.org/W6675894441","https://openalex.org/W6682968728","https://openalex.org/W6684415428","https://openalex.org/W6684921986","https://openalex.org/W6747473740","https://openalex.org/W6748839928"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2386410636","https://openalex.org/W2025663273","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4387019592","https://openalex.org/W4313679781","https://openalex.org/W4321463377","https://openalex.org/W3099153698","https://openalex.org/W3038962357"],"abstract_inverted_index":{"The":[0,16,138],"paper":[1,126],"focuses":[2],"on":[3,166],"development":[4],"of":[5,73,84,145,174],"model-free":[6,37],"and":[7,32,157],"distributed":[8,151],"Reinforcement":[9],"Learning":[10],"(RL)":[11],"algorithms":[12],"for":[13],"multi-agent":[14,86,90,168],"networks.":[15],"goal":[17],"is":[18],"to":[19,48,63,79,117],"learn":[20],"optimal":[21],"control":[22],"policies":[23],"directly":[24],"from":[25],"smart":[26],"agents\u2019":[27],"cooperative":[28,91],"interactions":[29],"among":[30],"themselves":[31],"with":[33,40],"the":[34,44,65,82,85,111,122,125,143,146,154,175],"environment.":[35],"In":[36,51,88],"RL":[38,170],"methods":[39],"continuous":[41],"state-space,":[42],"typically,":[43],"value":[45,66],"function":[46,67],"needs":[47],"be":[49,96],"approximated.":[50],"this":[52],"regard,":[53],"Deep":[54],"Neural":[55],"Networks":[56],"(DNNs)":[57],"provide":[58],"an":[59,99,103,160],"attractive":[60],"modeling":[61],"mechanism":[62],"approximate":[64],"using":[68,153],"sample":[69],"transitions.":[70],"Direct":[71],"utilization":[72],"DNN-based":[74],"single-agent":[75],"approaches,":[76],"however,":[77,105],"failed":[78],"fully":[80],"overcome":[81],"complexities":[83],"scenarios.":[87],"different":[89],"scenarios,":[92],"Kalman-based":[93],"methodologies":[94],"could":[95],"used":[97],"as":[98,114],"efficient":[100],"alternative.":[101],"Such":[102],"approach,":[104],"commonly":[106],"requires":[107],"a-priori":[108],"information":[109],"about":[110],"system":[112],"(such":[113],"noise":[115],"statistics)":[116],"perform":[118],"efficiently.":[119],"To":[120],"address":[121],"aforementioned":[123],"challenge,":[124],"proposes":[127],"a":[128,150,167],"Distributed":[129],"Hybrid":[130],"(multiple":[131],"model)":[132],"Kalman":[133],"Temporal":[134],"Difference":[135],"framework":[136,141],"(DH-KTD).":[137],"proposed":[139,176],"DH-KT":[140],"adapts":[142],"parameters":[144],"localized":[147],"filters":[148],"in":[149,159],"fashion":[152],"observed":[155],"states":[156],"rewards":[158],"optimized":[161],"fashion.":[162],"Experimental":[163],"results":[164],"based":[165],"benchmark":[169],"problem":[171],"illustrate":[172],"efficacy":[173],"framework.":[177]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}