{"id":"https://openalex.org/W4416749030","doi":"https://doi.org/10.1109/access.2025.3637842","title":"Evaluation of Efficient and Flexible Hardware\u2013Software Co-Design of Advantage Actor\u2013Critic Reinforcement Learning for Edge Deployment","display_name":"Evaluation of Efficient and Flexible Hardware\u2013Software Co-Design of Advantage Actor\u2013Critic Reinforcement Learning for Edge Deployment","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416749030","doi":"https://doi.org/10.1109/access.2025.3637842"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3637842","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3637842","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3637842","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120386279","display_name":"Chavakorn Somjaisuk","orcid":"https://orcid.org/0009-0001-3481-7962"},"institutions":[{"id":"https://openalex.org/I35568498","display_name":"Kochi University of Technology","ror":"https://ror.org/00rghrr56","country_code":"JP","type":"education","lineage":["https://openalex.org/I35568498"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chavakorn Somjaisuk","raw_affiliation_strings":["Department of Engineering, Kochi University of Technology, Kami, Kochi, Japan"],"raw_orcid":"https://orcid.org/0009-0001-3481-7962","affiliations":[{"raw_affiliation_string":"Department of Engineering, Kochi University of Technology, Kami, Kochi, Japan","institution_ids":["https://openalex.org/I35568498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065071055","display_name":"Wang Liao","orcid":"https://orcid.org/0000-0003-2134-5588"},"institutions":[{"id":"https://openalex.org/I35568498","display_name":"Kochi University of Technology","ror":"https://ror.org/00rghrr56","country_code":"JP","type":"education","lineage":["https://openalex.org/I35568498"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wang Liao","raw_affiliation_strings":["Department of Engineering, Kochi University of Technology, Kami, Kochi, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2134-5588","affiliations":[{"raw_affiliation_string":"Department of Engineering, Kochi University of Technology, Kami, Kochi, Japan","institution_ids":["https://openalex.org/I35568498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015621925","display_name":"Yukio Mitsuyama","orcid":"https://orcid.org/0000-0001-8151-0085"},"institutions":[{"id":"https://openalex.org/I35568498","display_name":"Kochi University of Technology","ror":"https://ror.org/00rghrr56","country_code":"JP","type":"education","lineage":["https://openalex.org/I35568498"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yukio Mitsuyama","raw_affiliation_strings":["Department of Engineering, Kochi University of Technology, Kami, Kochi, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8151-0085","affiliations":[{"raw_affiliation_string":"Department of Engineering, Kochi University of Technology, Kami, Kochi, Japan","institution_ids":["https://openalex.org/I35568498"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17495779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"204743","last_page":"204758"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.3626999855041504,"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":0.3626999855041504,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.09309999644756317,"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"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.07029999792575836,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6703000068664551},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6315000057220459},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.5885000228881836},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5680000185966492},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5476999878883362},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5189999938011169},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5056999921798706},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4496000111103058},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4316999912261963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8212000131607056},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6703000068664551},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6315000057220459},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.5885000228881836},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5680000185966492},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5056999921798706},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45509999990463257},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4302000105381012},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.42579999566078186},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.38089999556541443},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3776000142097473},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3767000138759613},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3276999890804291},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.3091000020503998},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C131017901","wikidata":"https://www.wikidata.org/wiki/Q170451","display_name":"Logic gate","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2533000111579895},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C89227174","wikidata":"https://www.wikidata.org/wiki/Q2388981","display_name":"Electric power system","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3637842","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3637842","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:be23f894f33d47feae61dfc500bf90c9","is_oa":true,"landing_page_url":"https://doaj.org/article/be23f894f33d47feae61dfc500bf90c9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 204743-204758 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3637842","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3637842","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1977655452","https://openalex.org/W2572023225","https://openalex.org/W2783963507","https://openalex.org/W2896893468","https://openalex.org/W2904195769","https://openalex.org/W2911087563","https://openalex.org/W2931767035","https://openalex.org/W3026443214","https://openalex.org/W3035681682","https://openalex.org/W3046229513","https://openalex.org/W3085986624","https://openalex.org/W3216656735","https://openalex.org/W4205382450","https://openalex.org/W4210397953","https://openalex.org/W4283772204","https://openalex.org/W4388221187","https://openalex.org/W4390828957","https://openalex.org/W4409640920","https://openalex.org/W6922480057"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3,35],"shown":[4],"remarkable":[5],"success":[6],"in":[7,48,129],"solving":[8],"sequential":[9],"decisionmaking":[10],"problems,":[11],"yet":[12],"deploying":[13,177],"these":[14],"algorithms":[15,179],"on":[16,37,41,75,92,180],"resource-constrained":[17,181],"edge":[18,73],"devices":[19],"remains":[20],"a":[21,62,76,155],"significant":[22],"challenge":[23],"due":[24],"to":[25,108,118,160],"limited":[26],"power":[27,140,164],"and":[28,85,95,104,132,166],"area":[29],"budgets.":[30],"While":[31],"prior":[32],"FPGA-based":[33],"research":[34],"centered":[36],"Q-learning":[38],"implementations,":[39],"studies":[40],"Actor\u2013Critic":[42,68],"methods":[43],"remain":[44],"relatively":[45],"limited,":[46],"particularly":[47],"the":[49,109,115,135,174],"context":[50],"of":[51,65,158,176],"low-cost":[52,77],"embedded":[53],"platforms.":[54],"This":[55],"paper":[56],"addresses":[57],"this":[58],"gap":[59],"by":[60],"presenting":[61],"hardware\u2013software":[63],"co-design":[64],"an":[66,143],"Advantage":[67],"(A2C)":[69],"framework":[70],"tailored":[71],"for":[72,187],"deployment":[74],"Field":[78],"Programmable":[79],"Gate":[80],"Array":[81],"(FPGA).":[82],"We":[83],"propose":[84],"evaluate":[86],"three":[87],"distinct":[88],"hardware":[89],"architectures,":[90],"focusing":[91],"resource":[93],"consumption":[94],"latency.":[96],"Our":[97],"hybrid":[98],"computation":[99],"model":[100],"offloads":[101],"feedforward":[102],"(FF)":[103],"backpropagation":[105],"(BP)":[106],"operations":[107],"FPGA\u2019s":[110],"programmable":[111],"logic":[112],"while":[113],"leveraging":[114],"processing":[116],"system":[117],"perform":[119],"weight":[120],"updates":[121],"with":[122,150],"PyTorch,":[123],"enabling":[124,183],"flexible":[125],"optimizer":[126],"selection.":[127],"Evaluated":[128],"CartPole-v1,":[130],"Acrobot-v1,":[131],"LunarLander-v2":[133],"environments,":[134],"resource-efficient":[136],"design":[137],"achieves":[138],"higher":[139],"efficiency":[141],"than":[142],"Intel":[144],"i9-11900K":[145],"CPU.":[146],"A":[147],"low-latency":[148],"variant":[149],"four":[151],"compute":[152],"units":[153],"demonstrates":[154],"throughput":[156],"increase":[157],"up":[159],"3.4\u00d7,":[161],"21.7\u00d7":[162],"better":[163],"efficiency,":[165],"21.6\u00d7":[167],"greater":[168],"energy":[169],"efficiency.":[170],"These":[171],"results":[172],"confirm":[173],"viability":[175],"A2C":[178],"FPGAs,":[182],"efficient":[184],"RL-based":[185],"solutions":[186],"practical":[188],"edge-computing":[189],"applications.":[190]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}