{"id":"https://openalex.org/W4415250838","doi":"https://doi.org/10.1109/hpec67600.2025.11196707","title":"Adaptive Policy Synchronization for Scalable Reinforcement Learning","display_name":"Adaptive Policy Synchronization for Scalable Reinforcement Learning","publication_year":2025,"publication_date":"2025-09-15","ids":{"openalex":"https://openalex.org/W4415250838","doi":"https://doi.org/10.1109/hpec67600.2025.11196707"},"language":"en","primary_location":{"id":"doi:10.1109/hpec67600.2025.11196707","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec67600.2025.11196707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5119896822","display_name":"Rodney Lafuente-Mercado","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rodney Lafuente-Mercado","raw_affiliation_strings":["MIT Lincoln Laboratory,Lexington,MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,Lexington,MA","institution_ids":["https://openalex.org/I4210122954"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5119896822"],"corresponding_institution_ids":["https://openalex.org/I4210122954"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16083969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.5788000226020813,"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":0.5788000226020813,"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":0.7936999797821045},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7321000099182129},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.7099999785423279},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5435000061988831},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.48890000581741333},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.426800012588501},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.42649999260902405}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7936999797821045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907000184059143},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7321000099182129},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.7099999785423279},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6417999863624573},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5435000061988831},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.426800012588501},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42649999260902405},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3513999879360199},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.3402999937534332},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.26019999384880066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec67600.2025.11196707","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec67600.2025.11196707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W3100789280","https://openalex.org/W4404387560"],"related_works":[],"abstract_inverted_index":{"Scaling":[0],"reinforcement":[1],"learning":[2,55],"(RL)":[3],"often":[4],"requires":[5],"running":[6],"environments":[7],"across":[8],"many":[9],"machines,":[10],"but":[11],"most":[12],"frameworks":[13],"tie":[14],"simulation,":[15],"training,":[16],"and":[17,47,88,99],"infrastructure":[18],"into":[19,92],"rigid":[20],"systems.":[21],"We":[22],"introduce":[23],"ClusterEnv,":[24],"a":[25],"lightweight":[26],"interface":[27],"for":[28],"distributed":[29],"environment":[30,45],"execution":[31],"that":[32,110],"preserves":[33],"the":[34,40,78],"familiar":[35],"Gymnasium":[36],"API.":[37],"ClusterEnv":[38,84],"uses":[39],"DETACH":[41],"pattern,":[42],"which":[43],"moves":[44],"reset()":[46],"step()":[48],"operations":[49],"to":[50],"remote":[51],"workers":[52,71],"while":[53,114],"keeping":[54],"centralized.":[56],"To":[57],"reduce":[58],"policy":[59],"staleness":[60],"without":[61],"heavy":[62],"communication,":[63],"we":[64],"propose":[65],"Adaptive":[66],"Policy":[67],"Synchronization":[68],"(APS),":[69],"where":[70],"request":[72],"updates":[73],"only":[74],"when":[75],"divergence":[76],"from":[77],"central":[79],"learner":[80],"grows":[81],"too":[82],"large.":[83],"supports":[85],"both":[86],"on-":[87],"off-policy":[89],"methods,":[90],"integrates":[91],"existing":[93],"training":[94],"code":[95,119],"with":[96],"minimal":[97],"changes,":[98],"runs":[100],"efficiently":[101],"on":[102,105],"clusters.":[103],"Experiments":[104],"discrete":[106],"control":[107],"tasks":[108],"show":[109],"APS":[111],"maintains":[112],"performance":[113],"cutting":[115],"synchronization":[116],"overhead.":[117],"Source":[118],"is":[120],"available":[121],"at":[122],"https://github.com/rodlaf/ClusterEnv.":[123]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-16T00:00:00"}