{"id":"https://openalex.org/W7215112819","doi":"https://doi.org/10.1038/s41598-026-73214-2","title":"A resource-efficient Q-learning algorithm using Boltzmann policy","display_name":"A resource-efficient Q-learning algorithm using Boltzmann policy","publication_year":2026,"publication_date":"2026-10-01","ids":{"openalex":"https://openalex.org/W7215112819","doi":"https://doi.org/10.1038/s41598-026-73214-2"},"language":"en","primary_location":{"id":"doi:10.1038/s41598-026-73214-2","doi":"https://doi.org/10.1038/s41598-026-73214-2","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-73214-2","pdf_url":"https://www.nature.com/articles/s41598-026-73214-2_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41598-026-73214-2_reference.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140170216","display_name":"Arwa S. Bazmalah","orcid":"https://orcid.org/0009-0006-4199-6862","observed_orcids":["https://orcid.org/0009-0006-4199-6862"]},"institutions":[{"id":"https://openalex.org/I319841309","display_name":"Hadhramout University","ror":"https://ror.org/02kv0px94","country_code":"YE","type":"education","lineage":["https://openalex.org/I319841309"]},{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY","YE"],"is_corresponding":false,"raw_author_name":"Arwa S. Bazmalah","raw_affiliation_strings":["Department of Computer Engineering, Faculty of Engineering & Petroleum, Hadhramout University, Hadhramout, Yemen","Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600, Bangi, Selangor, Malaysia"],"raw_orcid":"https://orcid.org/0009-0006-4199-6862","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Faculty of Engineering & Petroleum, Hadhramout University, Hadhramout, Yemen","institution_ids":["https://openalex.org/I319841309"]},{"raw_affiliation_string":"Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600, Bangi, Selangor, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002635711","display_name":"Noorfazila Binti Kamal","orcid":"https://orcid.org/0000-0002-4061-2699","observed_orcids":["https://orcid.org/0000-0002-4061-2699"]},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Noorfazila Kamal","raw_affiliation_strings":["Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600, Bangi, Selangor, Malaysia"],"raw_orcid":"https://orcid.org/0000-0002-4061-2699","affiliations":[{"raw_affiliation_string":"Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600, Bangi, Selangor, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073149525","display_name":"Kalaivani Chellappan","orcid":"https://orcid.org/0000-0002-2618-216X","observed_orcids":["https://orcid.org/0000-0002-2618-216X"]},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Kalaivani Chellappan","raw_affiliation_strings":["Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600, Bangi, Selangor, Malaysia"],"raw_orcid":"https://orcid.org/0000-0002-2618-216X","affiliations":[{"raw_affiliation_string":"Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600, Bangi, Selangor, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076824923","display_name":"Asraf Mohamed Moubark","orcid":"https://orcid.org/0000-0002-7596-5515","observed_orcids":["https://orcid.org/0000-0002-7596-5515"]},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Asraf Mohamed Moubark","raw_affiliation_strings":["Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600, Bangi, Selangor, Malaysia"],"raw_orcid":"https://orcid.org/0000-0002-7596-5515","affiliations":[{"raw_affiliation_string":"Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600, Bangi, Selangor, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140170216","display_name":"Arwa S. Bazmalah","orcid":"https://orcid.org/0009-0006-4199-6862","observed_orcids":["https://orcid.org/0009-0006-4199-6862"]},"institutions":[{"id":"https://openalex.org/I319841309","display_name":"Hadhramout University","ror":"https://ror.org/02kv0px94","country_code":"YE","type":"education","lineage":["https://openalex.org/I319841309"]},{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY","YE"],"is_corresponding":false,"raw_author_name":"Arwa S. Bazmalah","raw_affiliation_strings":["Department of Computer Engineering, Faculty of Engineering & Petroleum, Hadhramout University, Hadhramout, Yemen","Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600, Bangi, Selangor, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Faculty of Engineering & Petroleum, Hadhramout University, Hadhramout, Yemen","institution_ids":["https://openalex.org/I319841309"]},{"raw_affiliation_string":"Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600, Bangi, Selangor, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002635711"],"corresponding_institution_ids":["https://openalex.org/I885383172"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.61384168,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T13292","display_name":"Embedded Systems and FPGA Applications","score":0.5654000043869019,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T13292","display_name":"Embedded Systems and FPGA Applications","score":0.5654000043869019,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10904","display_name":"Embedded Systems Design Techniques","score":0.30250000953674316,"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/T12941","display_name":"Embedded Systems and FPGA Design","score":0.025800000876188278,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/exploration-exploitation-trade-off","display_name":"exploration-exploitation balance","score":0.8659999966621399},{"id":"https://openalex.org/keywords/fpga-architecture","display_name":"FPGA architecture","score":0.5699999928474426},{"id":"https://openalex.org/keywords/fixed-point-arithmetic","display_name":"fixed-point arithmetic","score":0.753000020980835},{"id":"https://openalex.org/keywords/resource-efficient-design","display_name":"resource-efficient design","score":0.5889999866485596},{"id":"https://openalex.org/keywords/power-efficiency","display_name":"power efficiency","score":0.765999972820282},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.5820000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6291999816894531},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5331000089645386},{"id":"https://openalex.org/C35304006","wikidata":"https://www.wikidata.org/wiki/Q5962","display_name":"Boltzmann constant","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.296099990606308},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26260000467300415},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2434999942779541},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.24240000545978546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22939999401569366},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.22380000352859497}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1038/s41598-026-73214-2","doi":"https://doi.org/10.1038/s41598-026-73214-2","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-73214-2","pdf_url":"https://www.nature.com/articles/s41598-026-73214-2_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1038/s41598-026-73214-2","doi":"https://doi.org/10.1038/s41598-026-73214-2","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-73214-2","pdf_url":"https://www.nature.com/articles/s41598-026-73214-2_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322699","display_name":"Universiti Kebangsaan Malaysia","ror":"https://ror.org/00bw8d226"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7215112819.pdf","grobid_xml":"https://content.openalex.org/works/W7215112819.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1820996291","https://openalex.org/W3046229513","https://openalex.org/W3125827992","https://openalex.org/W4234813165","https://openalex.org/W4376605461","https://openalex.org/W4397000255","https://openalex.org/W4404057302","https://openalex.org/W7104675531"],"related_works":["https://openalex.org/W7124452164","https://openalex.org/W3092023123","https://openalex.org/W2904195769","https://openalex.org/W4300597967","https://openalex.org/W3175606556","https://openalex.org/W2608459296","https://openalex.org/W3089396352","https://openalex.org/W7211942157","https://openalex.org/W3008730189","https://openalex.org/W3046229513"],"abstract_inverted_index":{"Q-learning":[0,42],"(QL)":[1],"faces":[2],"a":[3,40,92],"challenge":[4],"in":[5,88],"balancing":[6],"exploration":[7],"and":[8,24,91,121,132,151,159,175],"exploitation.":[9],"QL":[10,187],"typically":[11],"employs":[12],"an":[13],"\u03b5-greedy":[14,18],"policy.":[15],"However,":[16],"the":[17,46,57,64,72,77,108,112,135,145,163,184],"policy":[19,48],"leads":[20],"to":[21,34,68,82,127,155],"slow":[22],"convergence":[23,90],"excessive":[25],"resource":[26,95,103,192],"consumption":[27],"on":[28,56,181],"Field-Programmable":[29],"Gate":[30],"Arrays":[31],"(FPGAs)":[32],"due":[33],"unnecessary":[35],"exploration.":[36],"This":[37,85],"paper":[38],"proposes":[39],"hardware":[41,138],"architecture":[43,188],"that":[44],"integrates":[45],"Boltzmann":[47,65],"using":[49],"fixed-point":[50],"representation.":[51],"The":[52],"design":[53,74,110,165],"is":[54,153],"implemented":[55],"Genesys":[58],"2":[59],"Kintex7":[60],"(XC7K325T-2FFG900C)":[61],"FPGA.":[62],"Utilizing":[63],"policy's":[66],"ability":[67],"prioritize":[69],"optimal":[70],"actions,":[71],"present":[73],"significantly":[75],"reduces":[76],"number":[78],"of":[79,114,134,147,170],"iterations":[80],"required":[81],"update":[83],"states.":[84],"reduction":[86],"results":[87,99],"faster":[89],"more":[93],"efficient":[94],"allocation":[96],"strategy.":[97],"Experimental":[98],"demonstrate":[100],"improved":[101],"FPGA":[102,191],"efficiency.":[104],"For":[105],"16-bit":[106,173],"implementations,":[107,144],"proposed":[109,164,185],"limits":[111],"usage":[113,146],"Look-Up":[115],"Tables":[116],"(LUTs),":[117],"LUTRAMs,":[118,149],"Flip-Flops":[119],"(FFs),":[120],"Block":[122],"Random":[123],"Access":[124],"Memories":[125],"(BRAMs)":[126],"just":[128],"0.86%,":[129],"0.06%,":[130],"0.27%,":[131],"0.79%":[133],"total":[136],"available":[137],"resources,":[139],"respectively.":[140,161],"Similar":[141],"for":[142,172,177],"32-bit":[143,178],"LUTs,":[148],"FFs,":[150],"BRAMs":[152],"restricted":[154],"1.26%,":[156],"0.01%,":[157],"0.38%,":[158],"2.02%,":[160],"Moreover,":[162],"achieves":[166],"power":[167],"efficiency":[168],"improvements":[169],"46%":[171],"configurations":[174],"28%":[176],"configurations.":[179],"Based":[180],"these":[182],"results,":[183],"Boltzmann-based":[186],"effectively":[189],"optimizes":[190],"utilization":[193],"while":[194],"enhancing":[195],"overall":[196],"system":[197],"performance.":[198]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-02T00:00:00"}
