{"id":"https://openalex.org/W2771384842","doi":"https://doi.org/10.1109/iccad.2017.8203866","title":"Deep reinforcement learning: Framework, applications, and embedded implementations: Invited paper","display_name":"Deep reinforcement learning: Framework, applications, and embedded implementations: Invited paper","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2771384842","doi":"https://doi.org/10.1109/iccad.2017.8203866","mag":"2771384842"},"language":"en","primary_location":{"id":"doi:10.1109/iccad.2017.8203866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad.2017.8203866","pdf_url":null,"source":{"id":"https://openalex.org/S4363608376","display_name":"2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)","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":"2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://escholarship.org/content/qt5q33q2xm/qt5q33q2xm.pdf?t=p7suot","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101911274","display_name":"Hongjia Li","orcid":"https://orcid.org/0000-0001-7016-421X"},"institutions":[{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongjia Li","raw_affiliation_strings":["Dept. Electrical Engineering & Computer Science, Syracuse University, Syracuse, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. Electrical Engineering & Computer Science, Syracuse University, Syracuse, NY, USA","institution_ids":["https://openalex.org/I70983195"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055725891","display_name":"Tianshu Wei","orcid":"https://orcid.org/0000-0002-6322-6192"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianshu Wei","raw_affiliation_strings":["Dept. Electrical & computer Engineering, University of California, Riverside, CA, USA","Dept. Electrical & Computer Engineering, University of California, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. Electrical & computer Engineering, University of California, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"Dept. Electrical & Computer Engineering, University of California, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051490998","display_name":"Ao Ren","orcid":"https://orcid.org/0000-0002-2322-8038"},"institutions":[{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ao Ren","raw_affiliation_strings":["Syracuse University, Syracuse, NY, US","Dept. Electrical Engineering & Computer Science, Syracuse University, Syracuse, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Syracuse University, Syracuse, NY, US","institution_ids":["https://openalex.org/I70983195"]},{"raw_affiliation_string":"Dept. Electrical Engineering & Computer Science, Syracuse University, Syracuse, NY, USA","institution_ids":["https://openalex.org/I70983195"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020896290","display_name":"Qi Zhu","orcid":"https://orcid.org/0000-0002-7700-4099"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Zhu","raw_affiliation_strings":["Dept. Electrical & computer Engineering, University of California, Riverside, CA, USA","Dept. Electrical & Computer Engineering, University of California, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. Electrical & computer Engineering, University of California, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"Dept. Electrical & Computer Engineering, University of California, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100651384","display_name":"Yanzhi Wang","orcid":"https://orcid.org/0000-0002-3024-7990"},"institutions":[{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanzhi Wang","raw_affiliation_strings":["Dept. Electrical Engineering & Computer Science, Syracuse University, Syracuse, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. Electrical Engineering & Computer Science, Syracuse University, Syracuse, NY, USA","institution_ids":["https://openalex.org/I70983195"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":57,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"847","last_page":"854"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9983999729156494,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9983999729156494,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8452494144439697},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7969306111335754},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5320742130279541},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5201030969619751},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4855596721172333},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.47625088691711426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4624180495738983},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4481654167175293},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43924039602279663},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.23548060655593872},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.1404837965965271}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8452494144439697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7969306111335754},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5320742130279541},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5201030969619751},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4855596721172333},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.47625088691711426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4624180495738983},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4481654167175293},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43924039602279663},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.23548060655593872},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.1404837965965271},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccad.2017.8203866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad.2017.8203866","pdf_url":null,"source":{"id":"https://openalex.org/S4363608376","display_name":"2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)","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":"2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)","raw_type":"proceedings-article"},{"id":"pmh:oai:escholarship.org/ark:/13030/qt5q33q2xm","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/5q33q2xm","pdf_url":"https://escholarship.org/content/qt5q33q2xm/qt5q33q2xm.pdf?t=p7suot","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:qt5q33q2xm","is_oa":false,"landing_page_url":"http://www.escholarship.org/uc/item/5q33q2xm","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Li, H.; Wei, T.; Ren, A.; Zhu, Q.; & Wang, Y.(2017). Deep reinforcement learning: Framework, applications, and embedded implementations: Invited paper. Computer-Aided Design (ICCAD), 2017 IEEE/ACM International Conference. UC Riverside: Center for Environmental Research and Technology. Retrieved from: http://www.escholarship.org/uc/item/5q33q2xm","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:escholarship.org/ark:/13030/qt5q33q2xm","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/5q33q2xm","pdf_url":"https://escholarship.org/content/qt5q33q2xm/qt5q33q2xm.pdf?t=p7suot","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309532","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2771384842.pdf","grobid_xml":"https://content.openalex.org/works/W2771384842.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W2003056114","https://openalex.org/W2098470668","https://openalex.org/W2115211925","https://openalex.org/W2118955868","https://openalex.org/W2121863487","https://openalex.org/W2124682147","https://openalex.org/W2137451368","https://openalex.org/W2145339207","https://openalex.org/W2151770284","https://openalex.org/W2153947321","https://openalex.org/W2155968351","https://openalex.org/W2163605009","https://openalex.org/W2173248099","https://openalex.org/W2219959730","https://openalex.org/W2257979135","https://openalex.org/W2290548492","https://openalex.org/W2296101864","https://openalex.org/W2402098947","https://openalex.org/W2402859572","https://openalex.org/W2518281301","https://openalex.org/W2534761338","https://openalex.org/W2551814622","https://openalex.org/W2625874945","https://openalex.org/W2746553466","https://openalex.org/W2949168242","https://openalex.org/W2963864421","https://openalex.org/W4214717370","https://openalex.org/W4251091605","https://openalex.org/W4298857966","https://openalex.org/W6680776264","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2188872161","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"The":[0,31,130],"recent":[1],"breakthroughs":[2],"of":[3,27,36,54,106,132,153],"deep":[4,40,65],"reinforcement":[5],"learning":[6],"(DRL)":[7],"technique":[8,33,135],"in":[9,20,93,136,162],"Alpha":[10],"Go":[11],"and":[12,24,57,61,74,123,165],"playing":[13],"Atari":[14],"have":[15,141],"set":[16],"a":[17,159],"good":[18],"example":[19],"handling":[21],"large":[22],"state":[23],"actions":[25],"spaces":[26],"complicated":[28],"control":[29,128],"problems.":[30],"DRL":[32,86,134,155],"is":[34,101],"comprised":[35],"(i)":[37],"an":[38,63],"offline":[39],"neural":[41],"network":[42],"(DNN)":[43],"construction":[44],"phase,":[45,67],"which":[46,68,88,157],"derives":[47,70],"the":[48,55,71,84,104,110,116,133,148,154],"correlation":[49],"between":[50],"each":[51],"state-action":[52],"pair":[53],"system":[56,126],"its":[58],"value":[59,76],"function,":[60],"(ii)":[62],"online":[64],"Q-learning":[66],"adaptively":[69],"optimal":[72,127],"action":[73],"updates":[75],"estimates.":[77],"In":[78],"this":[79,145],"paper,":[80],"we":[81],"first":[82],"present":[83],"general":[85],"framework,":[87,156],"can":[89],"be":[90],"widely":[91],"utilized":[92],"many":[94],"applications":[95,140],"with":[96,169],"different":[97],"optimization":[98],"objectives.":[99],"This":[100],"followed":[102],"by":[103],"introduction":[105],"three":[107,138],"specific":[108],"applications:":[109],"cloud":[111],"computing":[112],"resource":[113],"allocation":[114],"problem,":[115,122],"residential":[117],"smart":[118],"grid":[119],"task":[120],"scheduling":[121],"building":[124],"HVAC":[125],"problem.":[129],"effectiveness":[131],"these":[137],"cyber-physical":[139],"been":[142],"validated.":[143],"Finally,":[144],"paper":[146],"investigates":[147],"stochastic":[149],"computing-based":[150],"hardware":[151],"implementations":[152],"consumes":[158],"significant":[160],"improvement":[161],"area":[163],"efficiency":[164],"power":[166],"consumption":[167],"compared":[168],"binary-based":[170],"implementation":[171],"counterparts.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}