{"id":"https://openalex.org/W4383097435","doi":"https://doi.org/10.1109/icra48891.2023.10160684","title":"Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote Computers","display_name":"Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote Computers","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383097435","doi":"https://doi.org/10.1109/icra48891.2023.10160684"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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/A5100322712","display_name":"Yan Wang","orcid":"https://orcid.org/0000-0002-5344-1884"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yan Wang","raw_affiliation_strings":["University of Alberta,Department of Computing Science,Edmonton,AB.,Canada,T6G 2E8"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta,Department of Computing Science,Edmonton,AB.,Canada,T6G 2E8","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103860806","display_name":"Gautham Vasan","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gautham Vasan","raw_affiliation_strings":["University of Alberta,Department of Computing Science,Edmonton,AB.,Canada,T6G 2E8"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta,Department of Computing Science,Edmonton,AB.,Canada,T6G 2E8","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102815213","display_name":"A. Rupam Mahmood","orcid":"https://orcid.org/0000-0002-2640-1844"},"institutions":[{"id":"https://openalex.org/I125680101","display_name":"Turing Institute","ror":"https://ror.org/02x2mw849","country_code":"GB","type":"facility","lineage":["https://openalex.org/I125680101"]},{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA","GB","US"],"is_corresponding":false,"raw_author_name":"A. Rupam Mahmood","raw_affiliation_strings":["University of Alberta,Department of Computing Science,Edmonton,AB.,Canada,T6G 2E8","CIFAR AI Chair, Alberta Machine Intelligence Institute (Amii)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta,Department of Computing Science,Edmonton,AB.,Canada,T6G 2E8","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"CIFAR AI Chair, Alberta Machine Intelligence Institute (Amii)","institution_ids":["https://openalex.org/I125680101","https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6526,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74416814,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"9435","last_page":"9441"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9916999936103821,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.7993981242179871},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.743366539478302},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6664933562278748},{"id":"https://openalex.org/keywords/workstation","display_name":"Workstation","score":0.6322641968727112},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6136524081230164},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5817930102348328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.580145537853241},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.45056620240211487},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4355786442756653},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37198418378829956},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3431360125541687},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09909528493881226},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07689094543457031}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7993981242179871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743366539478302},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6664933562278748},{"id":"https://openalex.org/C67953723","wikidata":"https://www.wikidata.org/wiki/Q192525","display_name":"Workstation","level":2,"score":0.6322641968727112},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6136524081230164},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5817930102348328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.580145537853241},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.45056620240211487},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4355786442756653},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37198418378829956},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3431360125541687},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09909528493881226},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07689094543457031},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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":37,"referenced_works":["https://openalex.org/W64088143","https://openalex.org/W1658008008","https://openalex.org/W2168231600","https://openalex.org/W2295130897","https://openalex.org/W2736601468","https://openalex.org/W2743759810","https://openalex.org/W2767050701","https://openalex.org/W2781726626","https://openalex.org/W2785738552","https://openalex.org/W2907537824","https://openalex.org/W2948013437","https://openalex.org/W2950268955","https://openalex.org/W2962899390","https://openalex.org/W2963170432","https://openalex.org/W2963796870","https://openalex.org/W2964227158","https://openalex.org/W2987973365","https://openalex.org/W3021708257","https://openalex.org/W3022566517","https://openalex.org/W3101442004","https://openalex.org/W3213752693","https://openalex.org/W4221141531","https://openalex.org/W4292213368","https://openalex.org/W6636881020","https://openalex.org/W6684859321","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6747924173","https://openalex.org/W6749115525","https://openalex.org/W6754615820","https://openalex.org/W6762919599","https://openalex.org/W6767084887","https://openalex.org/W6776438516","https://openalex.org/W6776867236","https://openalex.org/W6804314722","https://openalex.org/W6842050754","https://openalex.org/W6903351479"],"related_works":["https://openalex.org/W2045348955","https://openalex.org/W2352028719","https://openalex.org/W2584886384","https://openalex.org/W2378667902","https://openalex.org/W2791088446","https://openalex.org/W2052769075","https://openalex.org/W4206808270","https://openalex.org/W1999130367","https://openalex.org/W2122871747","https://openalex.org/W3114279067"],"abstract_inverted_index":{"Real-time":[0],"learning":[1,55,86,101,159],"is":[2,19,46,124,250,258],"crucial":[3],"for":[4,15,75,171,252,264,272],"robotic":[5,17,134],"agents":[6],"adapting":[7],"to":[8,20,31,48,65,73,94,169,269],"ever-changing,":[9],"non-stationary":[10],"environments.":[11],"A":[12],"common":[13],"setup":[14],"a":[16,26,35,43,54,84,113,116,133,137,149,164,181,192,233,254],"agent":[18],"have":[21],"two":[22,98,127],"different":[23],"computers":[24],"simultaneously:":[25],"resource-limited":[27,150],"local":[28,114,151],"computer":[29,38,72,184],"tethered":[30,235],"the":[32,51,68,89,122,158,172,210,213,221,237,259],"robot":[33],"and":[34,63,107,115,136,201],"powerful":[36,71,182,234],"remote":[37,117,165,183],"connected":[39,70],"wirelessly.":[40],"Given":[41],"such":[42],"setup,":[44],"it":[45],"unclear":[47],"what":[49],"extent":[50],"performance":[52,77,120,145,173,189,205,214,238],"of":[53,97,121,157,196,198,215,223,239],"system":[56,87,93,123,160,241,248,263],"can":[57,278],"be":[58,279],"affected":[59],"by":[60,220],"resource":[61],"limitations":[62],"how":[64],"efficiently":[66],"use":[67],"wirelessly":[69],"compensate":[74,170],"any":[76],"loss.":[78],"In":[79,225],"this":[80],"paper,":[81],"we":[82],"implement":[83],"real-time":[85,265],"called":[88],"Remote-Local":[90],"Distributed":[91],"(ReLoD)":[92],"distribute":[95],"computations":[96,156,197,229],"deep":[99],"reinforcement":[100],"(RL)":[102],"algorithms,":[103],"Soft":[104],"Actor-Critic":[105],"(SAC)":[106],"Proximal":[108],"Policy":[109],"Optimization":[110],"(PPO),":[111],"between":[112],"computer.":[118,152],"The":[119,275],"evaluated":[125],"on":[126,148,163,206,232,243],"vision-based":[128,273],"control":[129],"tasks":[130],"developed":[131],"using":[132,180,253],"arm":[135],"mobile":[138],"robot.":[139],"Our":[140],"results":[141],"show":[142],"that":[143,249,267],"SAC's":[144],"degrades":[146],"heavily":[147],"Strikingly,":[153],"when":[154,227],"all":[155,228],"are":[161],"deployed":[162],"workstation,":[166],"SAC":[167,199],"fails":[168],"loss,":[174],"indicating":[175],"that,":[176],"without":[177],"careful":[178],"consideration,":[179],"may":[185],"not":[186],"result":[187],"in":[188],"improvement.":[190],"However,":[191],"carefully":[193],"chosen":[194],"distribution":[195,222],"consistently":[200],"substantially":[202],"improves":[203],"its":[204],"both":[207],"tasks.":[208,274],"On":[209],"other":[211],"hand,":[212],"PPO":[216],"remains":[217,242],"largely":[218],"unaffected":[219],"computations.":[224],"addition,":[226],"happen":[230],"solely":[231],"computer,":[236],"our":[240],"par":[244],"with":[245],"an":[246],"existing":[247],"well-tuned":[251],"single":[255],"machine.":[256],"ReLoD":[257],"only":[260],"publicly":[261],"available":[262],"RL":[266],"applies":[268],"multiple":[270],"robots":[271],"source":[276],"code":[277],"found":[280],"at":[281],"https://github.com/rlai-lab/relod":[282]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
