{"id":"https://openalex.org/W3016772285","doi":"https://doi.org/10.1109/icaiic48513.2020.9065233","title":"Federated Reinforcement Learning for Controlling Multiple Rotary Inverted Pendulums in Edge Computing Environments","display_name":"Federated Reinforcement Learning for Controlling Multiple Rotary Inverted Pendulums in Edge Computing Environments","publication_year":2020,"publication_date":"2020-02-01","ids":{"openalex":"https://openalex.org/W3016772285","doi":"https://doi.org/10.1109/icaiic48513.2020.9065233","mag":"3016772285"},"language":"en","primary_location":{"id":"doi:10.1109/icaiic48513.2020.9065233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic48513.2020.9065233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5012832048","display_name":"Hyun-Kyo Lim","orcid":"https://orcid.org/0000-0002-8807-1158"},"institutions":[{"id":"https://openalex.org/I35886859","display_name":"Korea University of Technology and Education","ror":"https://ror.org/053nycv62","country_code":"KR","type":"education","lineage":["https://openalex.org/I35886859"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyun-Kyo Lim","raw_affiliation_strings":["Dept. of Interdisciplinary Program in Creative Engineering, Korea University of Technology and Education, Cheon-an, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Interdisciplinary Program in Creative Engineering, Korea University of Technology and Education, Cheon-an, Korea","institution_ids":["https://openalex.org/I35886859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061365692","display_name":"Ju-Bong Kim","orcid":"https://orcid.org/0000-0001-6406-3092"},"institutions":[{"id":"https://openalex.org/I35886859","display_name":"Korea University of Technology and Education","ror":"https://ror.org/053nycv62","country_code":"KR","type":"education","lineage":["https://openalex.org/I35886859"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ju-Bong Kim","raw_affiliation_strings":["Dept. of Computer Science Engineering, Korea University of Technology and Education, Cheon-an, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science Engineering, Korea University of Technology and Education, Cheon-an, Korea","institution_ids":["https://openalex.org/I35886859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012955600","display_name":"Chan-Myung Kim","orcid":"https://orcid.org/0000-0002-5286-9854"},"institutions":[{"id":"https://openalex.org/I35886859","display_name":"Korea University of Technology and Education","ror":"https://ror.org/053nycv62","country_code":"KR","type":"education","lineage":["https://openalex.org/I35886859"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chan-Myung Kim","raw_affiliation_strings":["Advanced Technology Research Center, Korea University of Technology and Education, Cheon-an, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Technology Research Center, Korea University of Technology and Education, Cheon-an, Korea","institution_ids":["https://openalex.org/I35886859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049149048","display_name":"Gyu-Young Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I35886859","display_name":"Korea University of Technology and Education","ror":"https://ror.org/053nycv62","country_code":"KR","type":"education","lineage":["https://openalex.org/I35886859"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gyu-Young Hwang","raw_affiliation_strings":["Dept. of Computer Science Engineering, Korea University of Technology and Education, Cheon-an, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science Engineering, Korea University of Technology and Education, Cheon-an, Korea","institution_ids":["https://openalex.org/I35886859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034729258","display_name":"Ho-Bin Choi","orcid":"https://orcid.org/0000-0002-2071-652X"},"institutions":[{"id":"https://openalex.org/I35886859","display_name":"Korea University of Technology and Education","ror":"https://ror.org/053nycv62","country_code":"KR","type":"education","lineage":["https://openalex.org/I35886859"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ho-bin Choi","raw_affiliation_strings":["Dept. of Computer Science Engineering, Korea University of Technology and Education, Cheon-an, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science Engineering, Korea University of Technology and Education, Cheon-an, Korea","institution_ids":["https://openalex.org/I35886859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027634067","display_name":"Youn\u2010Hee Han","orcid":"https://orcid.org/0000-0002-5835-7972"},"institutions":[{"id":"https://openalex.org/I35886859","display_name":"Korea University of Technology and Education","ror":"https://ror.org/053nycv62","country_code":"KR","type":"education","lineage":["https://openalex.org/I35886859"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youn-Hee Han","raw_affiliation_strings":["Dept. of Computer Science Engineering, Korea University of Technology and Education, Cheon-an, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science Engineering, Korea University of Technology and Education, Cheon-an, Korea","institution_ids":["https://openalex.org/I35886859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35886859"],"apc_list":null,"apc_paid":null,"fwci":2.07,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.89668394,"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":"463","last_page":"464"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9876999855041504,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9763000011444092,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.9291702508926392},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8145526051521301},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.7660976648330688},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.6009190678596497},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5966209173202515},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.5266641974449158},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5181304812431335},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5029134154319763},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.45211657881736755},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.44248756766319275},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.42568591237068176},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4220721125602722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41390857100486755},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.07947525382041931}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9291702508926392},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8145526051521301},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.7660976648330688},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.6009190678596497},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5966209173202515},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.5266641974449158},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5181304812431335},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5029134154319763},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.45211657881736755},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.44248756766319275},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.42568591237068176},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4220721125602722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41390857100486755},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.07947525382041931},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaiic48513.2020.9065233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic48513.2020.9065233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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":30,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1191599655","https://openalex.org/W1522301498","https://openalex.org/W1567145281","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2156737235","https://openalex.org/W2405578611","https://openalex.org/W2736601468","https://openalex.org/W2901974609","https://openalex.org/W2904890600","https://openalex.org/W2911450448","https://openalex.org/W2912139568","https://openalex.org/W2921254774","https://openalex.org/W2963184621","https://openalex.org/W2964121744","https://openalex.org/W2979766322","https://openalex.org/W2980955189","https://openalex.org/W3038028469","https://openalex.org/W3105018016","https://openalex.org/W4285723212","https://openalex.org/W4299802797","https://openalex.org/W4377562264","https://openalex.org/W6627932998","https://openalex.org/W6631190155","https://openalex.org/W6713835734","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6758713102","https://openalex.org/W6769171246"],"related_works":["https://openalex.org/W4322761281","https://openalex.org/W4238233472","https://openalex.org/W3111395152","https://openalex.org/W4313526662","https://openalex.org/W4313463218","https://openalex.org/W3106131444","https://openalex.org/W3216099748","https://openalex.org/W4205963435","https://openalex.org/W4312996489","https://openalex.org/W3214037210"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,29,86,105,117,192,198,206],"has":[2],"recently":[3],"been":[4],"studied":[5],"in":[6,141],"various":[7],"fields":[8],"and":[9,66,122,146,155,203],"also":[10,73,160],"used":[11],"to":[12,25,31,82,87,164],"optimally":[13],"control":[14,34,70,74],"real":[15,173],"devices":[16,39,174],"(e.g.,":[17],"robotic":[18],"arms).":[19],"In":[20],"this":[21,97],"paper,":[22],"we":[23,79,99,185],"try":[24],"allow":[26],"multiple":[27,51,172,180,201],"reinforcement":[28,85,104,191],"agents":[30,213],"learn":[32],"optimal":[33,69],"policy":[35,71,126],"on":[36,111],"their":[37,116],"own":[38],"of":[40],"the":[41,68,134,142,152,156,176,188,197,205],"same":[42,177],"type":[43],"but":[44],"with":[45,63,119],"slightly":[46],"different":[47],"dynamics.":[48],"For":[49],"such":[50],"devices,":[52,184,202],"there":[53],"is":[54],"no":[55],"guarantee":[56],"that":[57,168,187,204],"an":[58,148],"agent":[59,109,140],"who":[60],"interacts":[61],"only":[62],"one":[64],"device":[65,76,89,114],"learns":[67],"will":[72],"another":[75],"well.":[77],"Therefore,":[78],"may":[80],"need":[81],"apply":[83],"independent":[84,113],"each":[88,108,120,139],"individually,":[90],"which":[91],"requires":[92],"time-consuming":[93],"effort.":[94],"To":[95],"solve":[96,165],"problem,":[98],"propose":[100,147],"a":[101,124],"new":[102],"federated":[103,190],"architecture":[106],"where":[107],"working":[110],"its":[112],"shares":[115],"experience":[118],"other,":[121],"transfers":[123],"mature":[125],"model":[127,157],"parameters":[128],"into":[129,138],"other":[130],"agents.":[131],"We":[132,159],"incorporate":[133],"Actor-Critic":[135],"PPO":[136],"algorithm":[137],"proposed":[143,189],"collaborative":[144],"architecture,":[145],"efficient":[149],"procedure":[150],"for":[151,200],"gradient":[153],"sharing":[154],"transfer.":[158],"use":[161],"edge":[162],"computing":[163],"network":[166],"problems":[167],"occur":[169],"when":[170],"training":[171],"at":[175],"time.":[178],"Using":[179],"rotary":[181],"inverted":[182],"pendulum":[183],"demonstrate":[186],"scheme":[193],"can":[194,208],"effectively":[195],"facilitate":[196],"process":[199],"speed":[207],"be":[209],"faster":[210],"if":[211],"more":[212],"are":[214],"involved.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}