{"id":"https://openalex.org/W3123911006","doi":"https://doi.org/10.1109/globecom42002.2020.9322408","title":"Remote Reinforcement Learning over a Noisy Channel","display_name":"Remote Reinforcement Learning over a Noisy Channel","publication_year":2020,"publication_date":"2020-12-01","ids":{"openalex":"https://openalex.org/W3123911006","doi":"https://doi.org/10.1109/globecom42002.2020.9322408","mag":"3123911006"},"language":"en","primary_location":{"id":"doi:10.1109/globecom42002.2020.9322408","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom42002.2020.9322408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11380/1247335","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023623107","display_name":"Joan S. Pujol Roig","orcid":"https://orcid.org/0000-0001-9209-0207"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Joan S. Pujol Roig","raw_affiliation_strings":["Samsung Electronics R&D Institute UK, Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics R&D Institute UK, Surrey, UK","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016883501","display_name":"Den\u0131z G\u00fcnd\u00fcz","orcid":"https://orcid.org/0000-0002-7725-395X"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Deniz Gunduz","raw_affiliation_strings":["Imperial College London, London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5023623107"],"corresponding_institution_ids":["https://openalex.org/I4210117523"],"apc_list":null,"apc_paid":null,"fwci":0.9602,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.81827344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9962000250816345,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9947999715805054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9406430721282959},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.9230684041976929},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.795199990272522},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7537227272987366},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6061884164810181},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5793885588645935},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5515588521957397},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4913434088230133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48577526211738586},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46803855895996094},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4169672727584839},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.39085882902145386},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3690428137779236},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2897173762321472},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.2660767436027527},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.18547126650810242},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08282250165939331}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9406430721282959},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.9230684041976929},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.795199990272522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537227272987366},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6061884164810181},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5793885588645935},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5515588521957397},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4913434088230133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48577526211738586},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46803855895996094},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4169672727584839},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.39085882902145386},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3690428137779236},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2897173762321472},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2660767436027527},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.18547126650810242},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08282250165939331},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/globecom42002.2020.9322408","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom42002.2020.9322408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unimore.it:11380/1247335","is_oa":true,"landing_page_url":"http://hdl.handle.net/11380/1247335","pdf_url":null,"source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:iris.unimore.it:11380/1247335","is_oa":true,"landing_page_url":"http://hdl.handle.net/11380/1247335","pdf_url":null,"source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4540976096","display_name":null,"funder_award_id":"BEACON (No. 677854)","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"}],"funders":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2080213916","https://openalex.org/W2145339207","https://openalex.org/W2173248099","https://openalex.org/W2173564293","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2395575420","https://openalex.org/W2564324149","https://openalex.org/W2604283518","https://openalex.org/W2746553466","https://openalex.org/W2749807327","https://openalex.org/W2803155336","https://openalex.org/W2914351253","https://openalex.org/W2951799221","https://openalex.org/W2963000099","https://openalex.org/W2963477884","https://openalex.org/W2963588154","https://openalex.org/W2963681240","https://openalex.org/W2963717208","https://openalex.org/W2963864421","https://openalex.org/W2963937357","https://openalex.org/W2964338167","https://openalex.org/W2983400533","https://openalex.org/W2990330051","https://openalex.org/W3006919779","https://openalex.org/W4230100653","https://openalex.org/W4289363497","https://openalex.org/W4295846245","https://openalex.org/W4297789683","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6712181171","https://openalex.org/W6713411898","https://openalex.org/W6731193076","https://openalex.org/W6736622323","https://openalex.org/W6738795958","https://openalex.org/W6743367460","https://openalex.org/W6751139674","https://openalex.org/W6755542948","https://openalex.org/W6758763022"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W4323315247","https://openalex.org/W2294884454","https://openalex.org/W2364406457","https://openalex.org/W2173087131","https://openalex.org/W1997350370"],"abstract_inverted_index":{"A":[0],"collaborative":[1],"multi-agent":[2],"reinforcement":[3],"learning":[4,97,120],"(RL)":[5],"problem":[6],"is":[7,39],"considered,":[8],"where":[9],"agents":[10],"communicate":[11,56],"over":[12,60],"a":[13,19,26,30,42,51,61,67,86,113],"noisy":[14,62],"communication":[15,63,95],"channel":[16,128],"towards":[17],"achieving":[18],"common":[20],"goal.":[21],"In":[22,92],"particular,":[23],"we":[24],"consider":[25],"remote-controlled":[27,68],"version":[28,69],"of":[29,66,70,102,108],"single-agent":[31,72,80],"RL":[32,73],"problem,":[33],"in":[34],"which":[35],"the":[36,46,58,71,78,106,121,127],"system":[37],"state":[38],"observed":[40],"by":[41,50],"guide":[43,54],"agent,":[44],"while":[45],"actions":[47],"are":[48,99],"taken":[49,100],"scout.":[52],"The":[53],"can":[55],"to":[57],"scout":[59],"link,":[64],"reminiscent":[65],"problem.":[74],"This":[75],"transformation":[76],"turns":[77],"original":[79],"Markov":[81],"decision":[82],"process":[83],"(MDP)":[84],"into":[85,125],"two-agent":[87],"partially":[88],"observable":[89],"MDP":[90],"(POMDP).":[91],"conventional":[93],"systems,":[94],"and":[96,111],"tasks":[98],"care":[101],"separately.":[103],"We":[104],"show":[105],"suboptimality":[107],"this":[109],"approach,":[110],"propose":[112],"deep":[114],"Q-learning":[115],"solution":[116],"that":[117],"aims":[118],"at":[119],"optimal":[122],"policy":[123],"taking":[124],"account":[126],"impairments.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2021-02-01T00:00:00"}