{"id":"https://openalex.org/W4388581437","doi":"https://doi.org/10.1145/3624062.3624170","title":"Addressing Stale Gradients in Scalable Federated Deep Reinforcement Learning","display_name":"Addressing Stale Gradients in Scalable Federated Deep Reinforcement Learning","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388581437","doi":"https://doi.org/10.1145/3624062.3624170"},"language":"en","primary_location":{"id":"doi:10.1145/3624062.3624170","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624170","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624170","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624170","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018530397","display_name":"Justin Stanley","orcid":"https://orcid.org/0009-0009-8588-2631"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Justin Stanley","raw_affiliation_strings":["Iowa State University, United States of America"],"affiliations":[{"raw_affiliation_string":"Iowa State University, United States of America","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079359777","display_name":"Ali Jannesari","orcid":"https://orcid.org/0000-0001-8672-5317"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Jannesari","raw_affiliation_strings":["Iowa State University, United States of America"],"affiliations":[{"raw_affiliation_string":"Iowa State University, United States of America","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018530397"],"corresponding_institution_ids":["https://openalex.org/I173911158"],"apc_list":null,"apc_paid":null,"fwci":0.3497,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66579377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"932","last_page":"940"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9975000023841858,"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":0.9975000023841858,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9937000274658203,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9751999974250793,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.88718581199646},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.833991289138794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8306944370269775},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.8012800216674805},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.683965802192688},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.645538330078125},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4843505620956421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4081459045410156},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.23444652557373047},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.21445518732070923},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13011249899864197}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.88718581199646},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.833991289138794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8306944370269775},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.8012800216674805},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.683965802192688},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.645538330078125},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4843505620956421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4081459045410156},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.23444652557373047},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.21445518732070923},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13011249899864197}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3624062.3624170","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624170","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624170","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3624062.3624170","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624170","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624170","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388581437.pdf"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2150468603","https://openalex.org/W3148526481","https://openalex.org/W3183452672","https://openalex.org/W4310705874"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2168758875","https://openalex.org/W4246549241","https://openalex.org/W2410733619","https://openalex.org/W2963483475","https://openalex.org/W3138386522","https://openalex.org/W2499279132"],"abstract_inverted_index":{"Advancements":[0],"in":[1,36,42,86,113],"reinforcement":[2],"learning":[3,57],"(RL)":[4],"via":[5],"deep":[6],"neural":[7],"networks":[8],"have":[9,33],"enabled":[10],"their":[11],"application":[12],"to":[13,30,59,77,97,107,110],"a":[14,102],"variety":[15],"of":[16,105],"real-world":[17],"problems.":[18],"However,":[19],"these":[20,95],"applications":[21],"often":[22],"suffer":[23],"from":[24,55,93],"long":[25],"training":[26,32],"times.":[27],"While":[28],"attempts":[29],"distribute":[31],"been":[34],"successful":[35],"controlled":[37],"scenarios,":[38],"they":[39],"face":[40],"challenges":[41],"heterogeneous-capacity,":[43],"unstable,":[44],"and":[45,115],"privacy":[46],"critical":[47],"environments":[48],"([3],":[49],"[9]).":[50],"This":[51],"work":[52],"applies":[53],"concepts":[54],"federated":[56,73],"(FL)":[58],"distributed":[60],"RL,":[61],"specifically":[62],"addressing":[63],"the":[64,87],"stale":[65,83],"gradient":[66,84],"problem.":[67],"A":[68],"deterministic":[69],"framework":[70],"for":[71,81],"asynchronous":[72],"RL":[74],"is":[75],"utilized":[76],"explore":[78],"dynamic":[79],"methods":[80,96],"handling":[82],"updates":[85],"Arcade":[88],"Learning":[89],"Environment.":[90],"Experimental":[91],"results":[92],"applying":[94],"two":[98],"Atari-2600":[99],"games":[100],"demonstrate":[101],"relative":[103],"speedup":[104],"up":[106],"95%":[108],"compared":[109],"plain":[111],"A3C":[112],"large":[114],"unstable":[116],"federations.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-01-24T23:23:39.755997","created_date":"2025-10-10T00:00:00"}