{"id":"https://openalex.org/W4414414938","doi":"https://doi.org/10.48550/arxiv.2507.16249","title":"Multi-Agent Reinforcement Learning for Sample-Efficient Deep Neural Network Mapping","display_name":"Multi-Agent Reinforcement Learning for Sample-Efficient Deep Neural Network Mapping","publication_year":2025,"publication_date":"2025-07-22","ids":{"openalex":"https://openalex.org/W4414414938","doi":"https://doi.org/10.48550/arxiv.2507.16249"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2507.16249","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.16249","pdf_url":"https://arxiv.org/pdf/2507.16249","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.16249","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058825852","display_name":"Srivatsan Krishnan","orcid":"https://orcid.org/0000-0002-7148-5389"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Krishnan, Srivatsan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017417703","display_name":"Jason Jabbour","orcid":"https://orcid.org/0009-0001-5093-4106"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jabbour, Jason","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456041","display_name":"Dan Zhang","orcid":"https://orcid.org/0000-0002-7295-4837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Dan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046953322","display_name":"Natasha Jaques","orcid":"https://orcid.org/0000-0002-8413-9469"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaques, Natasha","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002971435","display_name":"Aleksandra Faust","orcid":"https://orcid.org/0000-0002-3268-8685"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Faust, Aleksandra","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052169592","display_name":"Shayegan Omidshafiei","orcid":"https://orcid.org/0000-0001-7758-1454"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Omidshafiei, Shayegan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000635267","display_name":"Vijay Janapa Reddi","orcid":"https://orcid.org/0000-0002-5259-7721"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reddi, Vijay Janapa","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5058825852"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13717","display_name":"Advanced Algorithms and Applications","score":0.607200026512146,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13717","display_name":"Advanced Algorithms and Applications","score":0.607200026512146,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14225","display_name":"Advanced Sensor and Control Systems","score":0.5564000010490417,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.5540000200271606,"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":0.840399980545044},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5860999822616577},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5688999891281128},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4855000078678131},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4375},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.43070000410079956},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.3749000132083893},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.34279999136924744}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.840399980545044},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7585999965667725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6571000218391418},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5860999822616577},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5688999891281128},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5081999897956848},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4855000078678131},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4375},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.43070000410079956},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2702000141143799},{"id":"https://openalex.org/C2778820799","wikidata":"https://www.wikidata.org/wiki/Q3454688","display_name":"Cost reduction","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C120822770","wikidata":"https://www.wikidata.org/wiki/Q5156355","display_name":"Competitive learning","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2507.16249","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.16249","pdf_url":"https://arxiv.org/pdf/2507.16249","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.16249","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.16249","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.16249","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.16249","pdf_url":"https://arxiv.org/pdf/2507.16249","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Mapping":[0],"deep":[1],"neural":[2],"networks":[3],"(DNNs)":[4],"to":[5,26,60,95,132],"hardware":[6],"is":[7,44],"critical":[8],"for":[9],"optimizing":[10],"latency,":[11],"energy":[12],"consumption,":[13],"and":[14,29,136],"resource":[15],"utilization,":[16],"making":[17],"it":[18],"a":[19,39,52,105],"cornerstone":[20],"of":[21],"high-performance":[22],"accelerator":[23],"design.":[24],"Due":[25],"the":[27,66,96],"vast":[28],"complex":[30],"mapping":[31,93],"space,":[32],"reinforcement":[33,55],"learning":[34,56,108],"(RL)":[35],"has":[36],"emerged":[37],"as":[38],"promising":[40],"approach-but":[41],"its":[42],"effectiveness":[43],"often":[45],"limited":[46],"by":[47,124],"sample":[48,113,122],"inefficiency.":[49],"We":[50],"present":[51],"decentralized":[53],"multi-agent":[54],"(MARL)":[57],"framework":[58,72],"designed":[59],"overcome":[61],"this":[62],"challenge.":[63],"By":[64],"distributing":[65],"search":[67],"across":[68],"multiple":[69,80],"agents,":[70],"our":[71,118],"accelerates":[73],"exploration.":[74],"To":[75],"avoid":[76],"inefficiencies":[77],"from":[78],"training":[79],"agents":[81,98],"in":[82],"parallel,":[83],"we":[84],"introduce":[85],"an":[86],"agent":[87],"clustering":[88],"algorithm":[89],"that":[90,110],"assigns":[91],"similar":[92],"parameters":[94],"same":[97],"based":[99],"on":[100],"correlation":[101],"analysis.":[102],"This":[103],"enables":[104],"decentralized,":[106],"parallelized":[107],"process":[109],"significantly":[111],"improves":[112,121],"efficiency.":[114],"Experimental":[115],"results":[116],"show":[117],"MARL":[119],"approach":[120],"efficiency":[123],"30-300x":[125],"over":[126],"standard":[127],"single-agent":[128],"RL,":[129],"achieving":[130],"up":[131],"32.61x":[133],"latency":[134],"reduction":[135,141],"16.45x":[137],"energy-delay":[138],"product":[139],"(EDP)":[140],"under":[142],"iso-sample":[143],"conditions.":[144]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}