{"id":"https://openalex.org/W2897601765","doi":"https://doi.org/10.1109/ijcnn.2018.8489519","title":"Impacts of Mathematical Optimizations on Reinforcement Learning Policy Performance","display_name":"Impacts of Mathematical Optimizations on Reinforcement Learning Policy Performance","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2897601765","doi":"https://doi.org/10.1109/ijcnn.2018.8489519","mag":"2897601765"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2018.8489519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1510571","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020399719","display_name":"Sam Green","orcid":"https://orcid.org/0000-0003-3742-0810"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Green","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, New Mexico, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, New Mexico, USA","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043569589","display_name":"Craig M. Vineyard","orcid":"https://orcid.org/0000-0002-4787-6160"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Craig M. Vineyard","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, New Mexico, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, New Mexico, USA","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018100877","display_name":"\u00c7etin Kaya Ko\u00e7","orcid":"https://orcid.org/0000-0002-2572-9565"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cetin Kaya Koc","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, New Mexico, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, New Mexico, USA","institution_ids":["https://openalex.org/I4210104735"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210104735"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"518","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":0.9991000294685364,"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":0.9991000294685364,"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":0.9970999956130981,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8334668278694153},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7847543358802795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5229278802871704},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5120347142219543},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5105334520339966},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5053048729896545},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.496721088886261},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.49540865421295166},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4685063660144806},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.46393564343452454},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.44083595275878906},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4295036792755127},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13230806589126587},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12135791778564453}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8334668278694153},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7847543358802795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5229278802871704},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5120347142219543},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5105334520339966},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5053048729896545},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.496721088886261},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.49540865421295166},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4685063660144806},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.46393564343452454},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.44083595275878906},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4295036792755127},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13230806589126587},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12135791778564453},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ijcnn.2018.8489519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1510571","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1510571","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:osti.gov:1513745","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1513745","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1510571","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1510571","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2209453243","display_name":null,"funder_award_id":"DE-NA0003525","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2214935549","display_name":null,"funder_award_id":"NA0003525","funder_id":"https://openalex.org/F4320338291","funder_display_name":"Sandia National Laboratories"},{"id":"https://openalex.org/G4903105778","display_name":null,"funder_award_id":"NA0003525","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4947178736","display_name":null,"funder_award_id":"-NA0003525","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5211897158","display_name":null,"funder_award_id":"DE-NA0003525","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G5339743583","display_name":null,"funder_award_id":"NA0003525","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G8279418378","display_name":null,"funder_award_id":"DE-NA0003525","funder_id":"https://openalex.org/F4320338291","funder_display_name":"Sandia National Laboratories"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320317153","display_name":"DeepMind","ror":"https://ror.org/00971b260"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W1841592590","https://openalex.org/W1902934009","https://openalex.org/W2114766824","https://openalex.org/W2119144962","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2156387975","https://openalex.org/W2266701264","https://openalex.org/W2267635276","https://openalex.org/W2279098554","https://openalex.org/W2300242332","https://openalex.org/W2405920868","https://openalex.org/W2512629640","https://openalex.org/W2524428287","https://openalex.org/W2604319603","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2951963285","https://openalex.org/W2962899390","https://openalex.org/W2963114950","https://openalex.org/W2963374099","https://openalex.org/W2963674932","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964299589","https://openalex.org/W4214717370","https://openalex.org/W4230563027","https://openalex.org/W4295262505","https://openalex.org/W4300769538","https://openalex.org/W6638018090","https://openalex.org/W6638632666","https://openalex.org/W6638783484","https://openalex.org/W6639703010","https://openalex.org/W6677103964","https://openalex.org/W6682889407","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6693397755","https://openalex.org/W6693721977","https://openalex.org/W6695314431","https://openalex.org/W6698200048","https://openalex.org/W6714058667","https://openalex.org/W6725411060","https://openalex.org/W6727208969","https://openalex.org/W6741002519","https://openalex.org/W6744354654","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2373300491","https://openalex.org/W1212596013","https://openalex.org/W2378744544","https://openalex.org/W2594301978","https://openalex.org/W2379704676","https://openalex.org/W3183118997","https://openalex.org/W3214410901","https://openalex.org/W3204400881","https://openalex.org/W3204296682","https://openalex.org/W2917767146"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNN)":[3],"now":[4],"outperform":[5],"competing":[6],"methods":[7],"in":[8,105],"many":[9,34],"academic":[10],"and":[11,36,49,57,60],"industrial":[12],"domains.":[13,195],"These":[14],"high-capacity":[15],"universal":[16],"function":[17],"approximators":[18],"have":[19,71],"recently":[20],"been":[21,72],"leveraged":[22],"by":[23,143],"deep":[24,114,149,225],"reinforcement":[25],"learning":[26],"(RL)":[27],"algorithms":[28,129],"to":[29,82,121,173,198],"obtain":[30],"impressive":[31],"results":[32,163],"for":[33,89,126,192],"control":[35],"decision":[37],"making":[38],"problems.":[39],"During":[40],"the":[41,55,86,97,140,200,217],"past":[42],"three":[43],"years,":[44],"research":[45],"toward":[46,216],"pruning,":[47],"quantization,":[48],"compression":[50],"of":[51,63,78,202,219],"DNNs":[52],"has":[53],"reduced":[54],"mathematical,":[56],"therefore":[58],"time":[59],"energy,":[61],"requirements":[62,77],"DNN-based":[64],"inference.":[65],"For":[66],"example,":[67],"DNN":[68,94,107,144],"optimization":[69,95,145],"techniques":[70,146],"developed":[73],"which":[74],"reduce":[75],"storage":[76],"VGG-16":[79],"from":[80,93],"552MB":[81],"11.3MB,":[83],"while":[84,176],"maintaining":[85],"full-model":[87],"accuracy":[88],"image":[90],"classification.":[91],"Building":[92],"results,":[96],"computer":[98],"architecture":[99],"community":[100],"is":[101,133],"taking":[102],"increasing":[103],"interest":[104],"exploring":[106],"hardware":[108,119],"accelerator":[109],"designs.":[110],"Based":[111],"on":[112,205],"recent":[113],"RL":[115,150,168,206,226],"performance,":[116,208],"we":[117],"expect":[118],"designers":[120],"begin":[122],"considering":[123],"architectures":[124],"appropriate":[125],"accelerating":[127],"these":[128,155],"too.":[130],"However,":[131],"it":[132],"currently":[134],"unknown":[135],"how,":[136],"when,":[137],"or":[138,222],"if":[139],"\u201cnoise\u201d":[141],"introduced":[142],"will":[147],"degrade":[148],"performance.":[151],"This":[152],"work":[153,210],"measures":[154],"impacts,":[156],"using":[157],"standard":[158],"OpenAI":[159],"Gym":[160],"benchmarks.":[161],"Our":[162],"show":[164],"that":[165,184],"mathematically":[166],"optimized":[167],"policies":[169],"can":[170],"perform":[171],"equally":[172],"full-precision":[174],"RL,":[175],"requiring":[177],"substantially":[178],"less":[179],"computation.":[180],"We":[181],"also":[182],"observe":[183],"different":[185,193],"optimizations":[186,204],"are":[187],"better":[188],"suited":[189],"than":[190],"others":[191],"problem":[194],"By":[196],"beginning":[197],"understand":[199],"impacts":[201],"mathematical":[203],"policy":[207],"this":[209],"serves":[211],"as":[212],"a":[213],"starting":[214],"point":[215],"development":[218],"low":[220],"power":[221],"high":[223],"performance":[224],"accelerators.":[227]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}