{"id":"https://openalex.org/W4312549996","doi":"https://doi.org/10.1109/iros47612.2022.9981565","title":"Cloud-Edge Training Architecture for Sim-to-Real Deep Reinforcement Learning","display_name":"Cloud-Edge Training Architecture for Sim-to-Real Deep Reinforcement Learning","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312549996","doi":"https://doi.org/10.1109/iros47612.2022.9981565"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981565","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5030370370","display_name":"Hongpeng Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Hongpeng Cao","raw_affiliation_strings":["Technical University of Munich (TUM), School of Engineering and Design,Munich,Germany","Technical University of Munich (TUM), School of Engineering and Design, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich (TUM), School of Engineering and Design,Munich,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technical University of Munich (TUM), School of Engineering and Design, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001116971","display_name":"Mirco Theile","orcid":"https://orcid.org/0000-0003-1574-8858"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mirco Theile","raw_affiliation_strings":["Technical University of Munich (TUM), School of Engineering and Design,Munich,Germany","Technical University of Munich (TUM), School of Engineering and Design, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich (TUM), School of Engineering and Design,Munich,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technical University of Munich (TUM), School of Engineering and Design, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082365719","display_name":"Federico G. Wyrwal","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Federico G. Wyrwal","raw_affiliation_strings":["Technical University of Munich (TUM), School of Engineering and Design,Munich,Germany","Technical University of Munich (TUM), School of Engineering and Design, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich (TUM), School of Engineering and Design,Munich,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technical University of Munich (TUM), School of Engineering and Design, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060442004","display_name":"Marco Caccamo","orcid":"https://orcid.org/0000-0003-2328-044X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marco Caccamo","raw_affiliation_strings":["Technical University of Munich (TUM), School of Engineering and Design,Munich,Germany","Technical University of Munich (TUM), School of Engineering and Design, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich (TUM), School of Engineering and Design,Munich,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technical University of Munich (TUM), School of Engineering and Design, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030370370"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":1.1427,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8038677,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9363","last_page":"9370"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9941999912261963,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9848999977111816,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7893935441970825},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7480466961860657},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6183436512947083},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5979465246200562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5216301083564758},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5042647123336792},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.48629245162010193},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4754766523838043},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.46539506316185},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.4630250036716461},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.45762714743614197},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4209536015987396},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3527182936668396},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34053701162338257},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32963404059410095},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09641069173812866},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.0910586416721344}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7893935441970825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480466961860657},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6183436512947083},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5979465246200562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5216301083564758},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5042647123336792},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.48629245162010193},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4754766523838043},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.46539506316185},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.4630250036716461},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.45762714743614197},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4209536015987396},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3527182936668396},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34053701162338257},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32963404059410095},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09641069173812866},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0910586416721344},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981565","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":42,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W305431326","https://openalex.org/W1595483645","https://openalex.org/W1977655452","https://openalex.org/W2017957151","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2170091282","https://openalex.org/W2201581102","https://openalex.org/W2530944449","https://openalex.org/W2575705757","https://openalex.org/W2741122588","https://openalex.org/W2767050701","https://openalex.org/W2772721022","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2907537824","https://openalex.org/W2912063360","https://openalex.org/W2962957005","https://openalex.org/W2962974944","https://openalex.org/W2963184939","https://openalex.org/W2963390419","https://openalex.org/W2963864421","https://openalex.org/W2967727187","https://openalex.org/W2968340082","https://openalex.org/W2990747716","https://openalex.org/W3029509103","https://openalex.org/W3101442004","https://openalex.org/W3126321819","https://openalex.org/W4248871477","https://openalex.org/W6635465357","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6721345134","https://openalex.org/W6728367041","https://openalex.org/W6742461812","https://openalex.org/W6746809867","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6756463683","https://openalex.org/W6765121789"],"related_works":["https://openalex.org/W2768698792","https://openalex.org/W4322761281","https://openalex.org/W4238233472","https://openalex.org/W4313526662","https://openalex.org/W3111395152","https://openalex.org/W4312996489","https://openalex.org/W3106131444","https://openalex.org/W3216099748","https://openalex.org/W4205963435","https://openalex.org/W4313463379"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,14],"(DRL)":[3],"is":[4,119],"a":[5,132,190,198,234],"promising":[6],"approach":[7],"to":[8,36,48,74,108,114,122,136,155,182,219],"solve":[9],"complex":[10],"control":[11,163,201],"tasks":[12],"by":[13],"policies":[15,26,51,67,105],"through":[16],"interactions":[17],"with":[18,111],"the":[19,22,38,57,61,75,80,96,99,103,123,141,147,149,156,161,166,173,184,215,239],"environment.":[20],"However,":[21],"training":[23,31,152,169,185,236],"of":[24,30,65,98,126,186],"DRL":[25,50,138,217],"requires":[27],"large":[28],"amounts":[29],"experiences,":[32],"making":[33],"it":[34],"impractical":[35],"learn":[37],"policy":[39],"directly":[40],"on":[41,94,189,197],"physical":[42,191,199],"systems.":[43],"Sim-to-real":[44],"approaches":[45],"leverage":[46],"simulations":[47],"pretrain":[49],"and":[52,90,151,158,223],"then":[53],"deploy":[54],"them":[55],"in":[56,140,144],"real":[58,142],"world.":[59],"Unfortunately,":[60],"direct":[62],"real-world":[63,112,127,207,235],"deployment":[64],"pretrained":[66,100,216],"usually":[68],"suffers":[69],"from":[70,165,245],"performance":[71],"deterioration":[72],"due":[73,121],"different":[76],"dynamics,":[77],"known":[78],"as":[79,87],"reality":[81,174],"gap.":[82],"Recent":[83],"sim-to-real":[84,179],"methods,":[85],"such":[86],"domain":[88,91],"randomization":[89],"adaptation,":[92],"focus":[93],"improving":[95],"robustness":[97],"agents.":[101],"Nevertheless,":[102],"simulation-trained":[104],"often":[106],"need":[107],"be":[109,243],"tuned":[110],"data":[113],"reach":[115],"optimal":[116],"performance,":[117],"which":[118],"challenging":[120],"high":[124],"cost":[125],"samples.":[128],"This":[129],"work":[130],"proposes":[131],"distributed":[133],"cloud-edge":[134],"architecture":[135,177,212],"train":[137],"agents":[139,188,218],"world":[143],"real-time.":[145],"In":[146],"architecture,":[148],"inference":[150],"are":[153],"assigned":[154],"edge":[157],"cloud,":[159],"separating":[160],"real-time":[162],"loop":[164],"computationally":[167],"expensive":[168],"loop.":[170],"To":[171],"overcome":[172],"gap,":[175],"our":[176,211],"exploits":[178],"transfer":[180],"strategies":[181],"continue":[183],"simulation-pretrained":[187],"system.":[192],"We":[193],"demonstrate":[194],"its":[195],"applicability":[196],"inverted-pendulum":[200],"system,":[202],"analyzing":[203],"critical":[204],"parameters.":[205],"The":[206],"experiments":[208],"show":[209],"that":[210],"can":[213,242],"adapt":[214],"unseen":[220],"dynamics":[221],"consistently":[222],"efficiently.":[224],"<sup":[225,228],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[226,229],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[227,230],"A":[231],"video":[232],"showing":[233],"process":[237],"under":[238],"proposed":[240],"method":[241],"found":[244],"https://youtu.be/hMY9-c0SST0.":[246]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}