{"id":"https://openalex.org/W4416004294","doi":"https://doi.org/10.1145/3731599.3767514","title":"RL4Sys: A Lightweight System-driven RL Framework for Drop-in Integration in System Optimization","display_name":"RL4Sys: A Lightweight System-driven RL Framework for Drop-in Integration in System Optimization","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416004294","doi":"https://doi.org/10.1145/3731599.3767514"},"language":null,"primary_location":{"id":"doi:10.1145/3731599.3767514","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767514","pdf_url":null,"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 '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731599.3767514","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiaxin Dong","orcid":"https://orcid.org/0009-0008-5275-7837"},"institutions":[{"id":"https://openalex.org/I210824098","display_name":"Wilmington University","ror":"https://ror.org/00jrtvk29","country_code":"US","type":"education","lineage":["https://openalex.org/I210824098"]},{"id":"https://openalex.org/I4210107789","display_name":"American University for Humanities","ror":"https://ror.org/01g790094","country_code":"US","type":"education","lineage":["https://openalex.org/I4210107789"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiaxin Dong","raw_affiliation_strings":["University of Delaware, Wilmington, USA"],"raw_orcid":"https://orcid.org/0009-0008-5275-7837","affiliations":[{"raw_affiliation_string":"University of Delaware, Wilmington, USA","institution_ids":["https://openalex.org/I4210107789","https://openalex.org/I210824098"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Md. Hasanur Rashid","orcid":"https://orcid.org/0009-0001-2622-936X"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md. Hasanur Rashid","raw_affiliation_strings":["University of Delaware, Newark, USA"],"raw_orcid":"https://orcid.org/0009-0001-2622-936X","affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101649586","display_name":"Helen Xu","orcid":"https://orcid.org/0000-0003-2232-3305"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Helen Xu","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":"https://orcid.org/0000-0003-2232-3305","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012002926","display_name":"Dong Dai","orcid":"https://orcid.org/0000-0003-4078-8149"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Dai","raw_affiliation_strings":["University of Delaware, Newark, Delaware, USA"],"raw_orcid":"https://orcid.org/0000-0003-4078-8149","affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, Delaware, USA","institution_ids":["https://openalex.org/I86501945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I210824098","https://openalex.org/I4210107789"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.16704823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1406","last_page":"1414"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6376000046730042,"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":0.6376000046730042,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.041099999099969864,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.03830000013113022,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.71670001745224},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6710000038146973},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6046000123023987},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4781000018119812},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4578999876976013},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.45649999380111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8406000137329102},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.71670001745224},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6710000038146973},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.656000018119812},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6046000123023987},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4781000018119812},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4578999876976013},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.45649999380111694},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C19527686","wikidata":"https://www.wikidata.org/wiki/Q1665453","display_name":"System integration","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3686999976634979},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.32429999113082886},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2937999963760376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731599.3767514","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767514","pdf_url":null,"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 '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3731599.3767514","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767514","pdf_url":null,"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 '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7817836276","display_name":null,"funder_award_id":"2008265, 2412345","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2546571074","https://openalex.org/W2562337727","https://openalex.org/W2905342215","https://openalex.org/W2982400926","https://openalex.org/W4296611641","https://openalex.org/W4388581266","https://openalex.org/W4411800408"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3],"achieved":[4],"notable":[5],"success":[6],"in":[7,54,141],"complex":[8],"decision-making":[9],"tasks":[10],"across":[11,105],"various":[12],"domains,":[13],"including":[14],"games,":[15],"autonomous":[16],"driving,":[17],"and":[18,51,88,103,110,134],"robotics.":[19],"Motivated":[20],"by":[21],"these":[22],"advances,":[23],"systems":[24,84,177],"researchers":[25],"have":[26],"explored":[27],"RL":[28,40,66,98,132,174],"for":[29,44,70,175],"optimizing":[30],"system":[31,55],"behavior.":[32],"However,":[33],"practical":[34],"deployment":[35],"remains":[36],"uncommon,":[37],"as":[38],"existing":[39],"frameworks":[41,133],"are":[42,100],"ill-suited":[43],"system-oriented":[45],"use":[46],"cases,":[47],"introducing":[48],"substantial":[49],"integration":[50],"runtime":[52,155],"overhead":[53,156],"software.":[56],"To":[57],"address":[58],"this":[59],"gap,":[60],"we":[61],"present":[62],"RL4Sys,":[63],"a":[64,76],"lightweight":[65],"framework":[67],"designed":[68],"specifically":[69],"seamless":[71],"system-level":[72],"integration.":[73],"RL4Sys":[74,125,167],"includes":[75],"minimal":[77],"client":[78],"that":[79,124,166],"embeds":[80],"easily":[81],"within":[82],"target":[83],"to":[85,113,137,145,158,172],"record":[86],"trajectories":[87],"run":[89],"inference":[90],"from":[91],"locally":[92],"cached":[93],"deep":[94],"policies.":[95],"RL4Sys\u2019s":[96],"remote":[97],"trainers":[99],"executed":[101],"asynchronously":[102],"distributed":[104],"servers,":[106],"leveraging":[107],"zero-copy":[108],"gRPC":[109],"adaptive":[111],"batching":[112],"update":[114],"policies":[115],"without":[116],"blocking":[117],"the":[118,127,146,159,170],"original":[119,160],"system.":[120,162],"Our":[121],"evaluation":[122],"shows":[123],"matches":[126],"convergence":[128],"behavior":[129],"of":[130],"conventional":[131],"achieves":[135],"up":[136],"220%":[138],"higher":[139],"throughput":[140],"environment-oriented":[142],"settings":[143],"compared":[144],"state-of-the-art":[147],"framework,":[148],"RLlib,":[149],"while":[150],"incurring":[151],"less":[152],"than":[153],"6%":[154],"relative":[157],"non-RL":[161],"These":[163],"results":[164],"indicate":[165],"substantially":[168],"lowers":[169],"barrier":[171],"deploying":[173],"real-world":[176],"optimization.":[178]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-07T00:00:00"}