{"id":"https://openalex.org/W2889068523","doi":"https://doi.org/10.1109/asap.2018.8445099","title":"Towards Hardware Accelerated Reinforcement Learning for Application-Specific Robotic Control","display_name":"Towards Hardware Accelerated Reinforcement Learning for Application-Specific Robotic Control","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2889068523","doi":"https://doi.org/10.1109/asap.2018.8445099","mag":"2889068523"},"language":"en","primary_location":{"id":"doi:10.1109/asap.2018.8445099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2018.8445099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP)","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/A5013193578","display_name":"Shengjia Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shengjia Shao","raw_affiliation_strings":["Imperial College, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018771543","display_name":"Jason Sheng-Hong Tsai","orcid":"https://orcid.org/0000-0002-3543-9211"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jason Tsai","raw_affiliation_strings":["Imperial College, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045585128","display_name":"Michal Mysior","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michal Mysior","raw_affiliation_strings":["Imperial College, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057940557","display_name":"Wayne Luk","orcid":"https://orcid.org/0000-0002-6750-927X"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wayne Luk","raw_affiliation_strings":["Imperial College, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110651248","display_name":"Thomas Chau","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Chau","raw_affiliation_strings":["Imperial College, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055182928","display_name":"Alexander Warren","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alexander Warren","raw_affiliation_strings":["Intel Corporation, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, United Kingdom","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112243321","display_name":"Ben Jeppesen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ben Jeppesen","raw_affiliation_strings":["Intel Corporation, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, United Kingdom","institution_ids":["https://openalex.org/I4210158342"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6896,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.88240095,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9898999929428101,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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":0.9347434043884277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7825477123260498},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.618242621421814},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.6107935905456543},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5889756679534912},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47129690647125244},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.46145567297935486},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.326168954372406},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3071621358394623}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9347434043884277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7825477123260498},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.618242621421814},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.6107935905456543},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5889756679534912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47129690647125244},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.46145567297935486},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.326168954372406},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3071621358394623}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asap.2018.8445099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2018.8445099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP)","raw_type":"proceedings-article"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/64190","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/64190","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP)","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6200000047683716}],"awards":[{"id":"https://openalex.org/G7493804148","display_name":null,"funder_award_id":"EP/N031768/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G774180880","display_name":null,"funder_award_id":"EP/P010040/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W1977655452","https://openalex.org/W2006903949","https://openalex.org/W2158782408","https://openalex.org/W2257979135","https://openalex.org/W2342662072","https://openalex.org/W2572023225","https://openalex.org/W2575705757","https://openalex.org/W2743287738","https://openalex.org/W2763502612","https://openalex.org/W2963641140","https://openalex.org/W6638018090","https://openalex.org/W6704571135"],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4200391368","https://openalex.org/W4380318855","https://openalex.org/W2096844293","https://openalex.org/W2363944576","https://openalex.org/W2351041855","https://openalex.org/W2570254841","https://openalex.org/W2742986847"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"is":[3,146],"an":[4,11,39,95],"area":[5],"of":[6,63,71,94,172],"machine":[7],"learning":[8,129],"in":[9,59,111],"which":[10,55,109],"agent":[12,22],"interacts":[13],"with":[14],"the":[15,26,32,69,142,157,170],"environment":[16,27],"by":[17],"making":[18],"sequential":[19],"decisions.":[20],"The":[21,79],"receives":[23],"reward":[24],"from":[25],"based":[28,102],"on":[29,103,132],"how":[30],"good":[31],"decisions":[33],"are":[34,89],"and":[35,134,164],"tries":[36],"to":[37,67,91,148,163],"find":[38],"optimal":[40],"decision-making":[41],"policy":[42,65,100,145],"that":[43,156],"maximises":[44],"its":[45],"longterm":[46],"cumulative":[47],"reward.":[48],"This":[49],"paper":[50],"presents":[51],"a":[52,72,112,117,149],"novel":[53],"approach":[54,80],"has":[56,81],"showon":[57],"promise":[58],"applying":[60],"accelerated":[61],"simulation":[62],"RL":[64,99,144],"training":[66,101],"automating":[68],"control":[70],"real":[73,150],"robot":[74,151],"arm":[75,159],"for":[76,98],"specific":[77],"applications.":[78],"two":[82],"steps.":[83],"First,":[84],"design":[85],"space":[86],"exploration":[87],"techniques":[88],"developed":[90],"enhance":[92],"performance":[93],"FPGA":[96,119],"accelerator":[97],"Trust":[104],"Region":[105],"Policy":[106],"Optimisation":[107],"(TRPO),":[108],"results":[110],"43%":[113],"speed":[114,125,137],"improvement":[115],"over":[116],"previous":[118],"implementation,":[120],"while":[121],"achieving":[122],"4.65":[123],"times":[124,136],"up":[126,138,166],"against":[127,139],"deep":[128],"libraries":[130],"running":[131],"GPU":[133],"19.29":[135],"CPU.":[140],"Second,":[141],"trained":[143,158],"transferred":[147],"arm.":[152],"Our":[153],"experiments":[154],"show":[155],"can":[160],"successfully":[161],"reach":[162],"pick":[165],"predefined":[167],"objects,":[168],"demonstrating":[169],"feasibility":[171],"our":[173],"approach.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}