{"id":"https://openalex.org/W2978696242","doi":"https://doi.org/10.1109/ijcnn.2019.8852451","title":"Accelerating the Deep Reinforcement Learning with Neural Network Compression","display_name":"Accelerating the Deep Reinforcement Learning with Neural Network Compression","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2978696242","doi":"https://doi.org/10.1109/ijcnn.2019.8852451","mag":"2978696242"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8852451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","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/A5100449658","display_name":"Hongjie Zhang","orcid":"https://orcid.org/0000-0001-9565-3378"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongjie Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017872137","display_name":"Zhuocheng He","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuocheng He","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100386755","display_name":"Jing Li","orcid":"https://orcid.org/0000-0003-2075-5155"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.8678,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.81319422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"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":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.992900013923645,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9872000217437744,"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":0.8672482371330261},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7824643850326538},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7707729339599609},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.729990541934967},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6446490287780762},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.623397707939148},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5883893966674805},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.47564268112182617},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44582992792129517},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.4403197765350342},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.43354204297065735},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.41362541913986206}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8672482371330261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7824643850326538},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7707729339599609},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.729990541934967},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6446490287780762},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.623397707939148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5883893966674805},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.47564268112182617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44582992792129517},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.4403197765350342},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.43354204297065735},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.41362541913986206},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/ijcnn.2019.8852451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1658008008","https://openalex.org/W1821462560","https://openalex.org/W2119144962","https://openalex.org/W2126565096","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2156737235","https://openalex.org/W2296073425","https://openalex.org/W2300242332","https://openalex.org/W2555255624","https://openalex.org/W2584377191","https://openalex.org/W2616729100","https://openalex.org/W2741401130","https://openalex.org/W2766447205","https://openalex.org/W2789517807","https://openalex.org/W2803740478","https://openalex.org/W2963674921","https://openalex.org/W2963674932","https://openalex.org/W2963875819","https://openalex.org/W2963985863","https://openalex.org/W2964043796","https://openalex.org/W2964299589","https://openalex.org/W3103780890","https://openalex.org/W4297797010","https://openalex.org/W4298845604","https://openalex.org/W6636881020","https://openalex.org/W6677580257","https://openalex.org/W6683195989","https://openalex.org/W6692846177","https://openalex.org/W6698200048","https://openalex.org/W6715102896","https://openalex.org/W6730065366","https://openalex.org/W6732837357","https://openalex.org/W6748440607","https://openalex.org/W6748638692","https://openalex.org/W6751398007"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W2891987081"],"abstract_inverted_index":{"Acceleration":[0],"in":[1,36],"deep":[2,110],"reinforcement":[3,111],"learning":[4],"has":[5],"attracted":[6],"the":[7,21,24,32,41,54,68,71,75,86,91,105,136,144,156,172,175,181,192,195,207],"attention":[8],"of":[9,34,49,70,109,174,194],"researchers.":[10],"Many":[11],"parallel":[12,61],"training":[13,25,77,92,100,107,209],"frameworks":[14],"have":[15],"been":[16],"proposed":[17],"to":[18,53,65,73,89,103,118,155,185],"speed":[19,66,142,205],"up":[20,67,143,206],"sampling":[22],"and":[23,122,167],"by":[26,211],"running":[27],"multiple":[28],"agents":[29],"simultaneously.":[30],"However,":[31],"bottleneck":[33],"performance":[35,220],"a":[37,47,98,130],"single":[38],"agent":[39,72],"is":[40,85,129],"neural":[42,116,132],"network":[43,128,133,149,166,169],"prediction":[44,69],"which":[45,140,189],"takes":[46],"lot":[48],"time":[50,88],"as":[51,81],"compared":[52],"rapid":[55],"environmental":[56],"changes.":[57],"Different":[58],"from":[59,93,135],"these":[60],"frameworks,":[62],"we":[63,82,179],"try":[64],"accelerate":[74,90,104],"entire":[76],"process.":[78],"As":[79],"far":[80],"know,":[83],"this":[84,94],"first":[87],"perspective.":[95],"We":[96],"propose":[97],"novel":[99],"framework":[101],"NNC-DRL":[102,113,203],"whole":[106,208],"process":[108,210],"learning.":[112],"uses":[114],"different":[115],"networks":[117],"represent":[119],"target":[120,137,147,168],"policy":[121,127,138,148,154,158,162,187],"behavior":[123,126,157,165],"policy.":[124],"The":[125,146,160,197],"smaller":[131],"derived":[134],"network,":[139],"could":[141,190],"prediction.":[145],"will":[150,170],"transfer":[151],"its":[152],"latest":[153],"network.":[159],"inconsistent":[161],"distribution":[163],"between":[164],"degrade":[171],"convergence":[173,193],"training.":[176,196],"In":[177],"NNC-DRL,":[178],"introduce":[180],"Important":[182],"Sampling":[183],"technique":[184],"estimate":[186],"gradient,":[188],"improve":[191],"experiments":[198],"show":[199],"that":[200],"our":[201],"approach":[202],"can":[204],"about":[212],"10-20%":[213],"on":[214],"Atari":[215],"2600":[216],"games":[217],"with":[218],"little":[219],"loss.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}