{"id":"https://openalex.org/W4200398796","doi":"https://doi.org/10.1109/a-sscc53895.2021.9634810","title":"An Energy-Efficient Deep Reinforcement Learning FPGA Accelerator for Online Fast Adaptation with Selective Mixed-precision Re-training","display_name":"An Energy-Efficient Deep Reinforcement Learning FPGA Accelerator for Online Fast Adaptation with Selective Mixed-precision Re-training","publication_year":2021,"publication_date":"2021-11-07","ids":{"openalex":"https://openalex.org/W4200398796","doi":"https://doi.org/10.1109/a-sscc53895.2021.9634810"},"language":"en","primary_location":{"id":"doi:10.1109/a-sscc53895.2021.9634810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/a-sscc53895.2021.9634810","pdf_url":null,"source":{"id":"https://openalex.org/S4363608516","display_name":"2021 IEEE Asian Solid-State Circuits Conference (A-SSCC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Asian Solid-State Circuits Conference (A-SSCC)","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/A5015963917","display_name":"Wooyoung Jo","orcid":"https://orcid.org/0000-0003-3598-3572"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Wooyoung Jo","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST)"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010104451","display_name":"Juhyoung Lee","orcid":"https://orcid.org/0000-0002-2100-1024"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhyoung Lee","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST)"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103008586","display_name":"Seunghyun Park","orcid":"https://orcid.org/0000-0003-4044-5349"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seunghyun Park","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST)"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077896259","display_name":"Hoi\u2010Jun Yoo","orcid":"https://orcid.org/0000-0002-6661-4879"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hoi-Jun Yoo","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST)"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015963917"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.2513,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.51131053,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9882000088691711,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9864000082015991,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9027656316757202},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7730789184570312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7419894337654114},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6483567953109741},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5290096402168274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4441917836666107},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37349146604537964},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.28003016114234924}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9027656316757202},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7730789184570312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7419894337654114},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6483567953109741},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5290096402168274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4441917836666107},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37349146604537964},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.28003016114234924},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/a-sscc53895.2021.9634810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/a-sscc53895.2021.9634810","pdf_url":null,"source":{"id":"https://openalex.org/S4363608516","display_name":"2021 IEEE Asian Solid-State Circuits Conference (A-SSCC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Asian Solid-State Circuits Conference (A-SSCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2583528914","https://openalex.org/W2931767035","https://openalex.org/W3126539204","https://openalex.org/W3213742958","https://openalex.org/W6732951832"],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W4306904969","https://openalex.org/W4200391368","https://openalex.org/W2355315220","https://openalex.org/W2210979487","https://openalex.org/W2138720691","https://openalex.org/W2074043759","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474"],"abstract_inverted_index":{"Recently,":[0],"deep":[1,61],"reinforcement":[2],"learning":[3,62],"(DRL)":[4],"has":[5],"shown":[6],"human-level":[7],"performances":[8],"in":[9,72],"sequential":[10],"decision-making":[11],"problems":[12],"including":[13],"a":[14,50,53],"gaming":[15],"agent":[16,87,97],"and":[17,56,88],"robot":[18],"control":[19],"[1].":[20],"Especially,":[21],"DRL":[22,45,51,67,86],"supports":[23],"autonomous":[24],"adaptation":[25],"of":[26,43,49],"edge":[27],"devices":[28],"to":[29,33,98,100],"unknown":[30],"environments":[31],"thanks":[32],"its":[34],"distinct":[35],"characteristics.":[36],"Fig.":[37],"1":[38],"shows":[39],"the":[40,44,57,73,85,89,96],"basic":[41],"components":[42],"system.":[46],"It":[47],"consists":[48],"agent,":[52],"replay":[54,74],"buffer,":[55],"environment.":[58,90],"Unlike":[59],"traditional":[60],"which":[63],"requires":[64],"labeled":[65],"data,":[66],"training":[68,93],"utilizes":[69],"experiences":[70,78],"stored":[71,77],"buffer.":[75],"The":[76],"are":[79],"generated":[80],"by":[81],"repetitive":[82],"interaction":[83],"between":[84],"This":[91],"trial-and-error-based":[92],"method":[94],"enables":[95],"adapt":[99],"sudden":[101],"environmental":[102],"changes.":[103]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}