{"id":"https://openalex.org/W2999204576","doi":"https://doi.org/10.1109/jstsp.2020.2967566","title":"PoPS: Policy Pruning and Shrinking for Deep Reinforcement Learning","display_name":"PoPS: Policy Pruning and Shrinking for Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-01-17","ids":{"openalex":"https://openalex.org/W2999204576","doi":"https://doi.org/10.1109/jstsp.2020.2967566","mag":"2999204576"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2020.2967566","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2020.2967566","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.05012","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008407587","display_name":"Dor Livne","orcid":"https://orcid.org/0000-0002-8632-7535"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Dor Livne","raw_affiliation_strings":["School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer Sheva, Israel"],"raw_orcid":"https://orcid.org/0000-0002-8632-7535","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer Sheva, Israel","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066085947","display_name":"Kobi Cohen","orcid":"https://orcid.org/0000-0003-0532-009X"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Kobi Cohen","raw_affiliation_strings":["School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer Sheva, Israel"],"raw_orcid":"https://orcid.org/0000-0003-0532-009X","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer Sheva, Israel","institution_ids":["https://openalex.org/I124227911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3853,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.93610972,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"14","issue":"4","first_page":"789","last_page":"801"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9919000267982483,"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/computer-science","display_name":"Computer science","score":0.7985862493515015},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7651593685150146},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7363298535346985},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6002523899078369},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5645716190338135},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5145573019981384},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.48661503195762634},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4643213152885437},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42504650354385376},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41572698950767517}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7985862493515015},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7651593685150146},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7363298535346985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6002523899078369},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5645716190338135},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5145573019981384},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.48661503195762634},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4643213152885437},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42504650354385376},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41572698950767517},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2020.2967566","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2020.2967566","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2001.05012","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.05012","pdf_url":"https://arxiv.org/pdf/2001.05012","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.05012","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.05012","pdf_url":"https://arxiv.org/pdf/2001.05012","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G46667588","display_name":null,"funder_award_id":"2017723","funder_id":"https://openalex.org/F4320320950","funder_display_name":"United States-Israel Binational Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320320950","display_name":"United States-Israel Binational Science Foundation","ror":"https://ror.org/00j8z2m73"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1757796397","https://openalex.org/W1821462560","https://openalex.org/W2119144962","https://openalex.org/W2134797427","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2161591461","https://openalex.org/W2285660444","https://openalex.org/W2294370754","https://openalex.org/W2395575420","https://openalex.org/W2409436280","https://openalex.org/W2495425901","https://openalex.org/W2565335599","https://openalex.org/W2580175322","https://openalex.org/W2592120495","https://openalex.org/W2612336410","https://openalex.org/W2614392736","https://openalex.org/W2735189290","https://openalex.org/W2746553466","https://openalex.org/W2756085244","https://openalex.org/W2764043458","https://openalex.org/W2791845808","https://openalex.org/W2886851211","https://openalex.org/W2887579771","https://openalex.org/W2893585013","https://openalex.org/W2898754723","https://openalex.org/W2912108923","https://openalex.org/W2940478336","https://openalex.org/W2949941638","https://openalex.org/W2951799221","https://openalex.org/W2952899695","https://openalex.org/W2962883549","https://openalex.org/W2963079995","https://openalex.org/W2963363373","https://openalex.org/W2963387524","https://openalex.org/W2963674932","https://openalex.org/W2964043796","https://openalex.org/W2964228333","https://openalex.org/W2964299589","https://openalex.org/W2970500560","https://openalex.org/W3012943290","https://openalex.org/W3103559770","https://openalex.org/W4245873651","https://openalex.org/W4298857966","https://openalex.org/W4300109888","https://openalex.org/W6637967152","https://openalex.org/W6638523607","https://openalex.org/W6677580257","https://openalex.org/W6679909955","https://openalex.org/W6683826617","https://openalex.org/W6685444567","https://openalex.org/W6692846177","https://openalex.org/W6712181171","https://openalex.org/W6723181079","https://openalex.org/W6732665253","https://openalex.org/W6732837357","https://openalex.org/W6734062232","https://openalex.org/W6734554788","https://openalex.org/W6744495609","https://openalex.org/W6745148473","https://openalex.org/W6753490951","https://openalex.org/W6755543212","https://openalex.org/W6761890098","https://openalex.org/W6780559895","https://openalex.org/W7037238757"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W3000197790","https://openalex.org/W4315865067","https://openalex.org/W2979433843","https://openalex.org/W3208304128"],"abstract_inverted_index":{"The":[0,142],"recent":[1,66],"success":[2,73],"of":[3,18,56,78,110,139,159,178,200],"deep":[4],"neural":[5],"networks":[6],"(DNNs)":[7],"for":[8,197],"function":[9],"approximation":[10],"in":[11,24,59,74,80,92,112,204],"reinforcement":[12],"learning":[13,161],"has":[14],"triggered":[15],"the":[16,54,76,93,101,106,113,140,157,164,175,181,198],"development":[17],"Deep":[19],"Reinforcement":[20],"Learning":[21],"(DRL)":[22],"algorithms":[23,58,69,85],"various":[25],"fields,":[26],"such":[27],"as":[28],"robotics,":[29],"computer":[30,35],"games,":[31],"natural":[32],"language":[33],"processing,":[34],"vision,":[36],"sensing":[37],"systems,":[38],"and":[39,49,116,124,152,187,202],"wireless":[40],"networking.":[41],"Unfortunately,":[42],"DNNs":[43,79],"suffer":[44,86],"from":[45,87],"high":[46],"computational":[47],"cost":[48],"memory":[50],"consumption,":[51],"which":[52],"limits":[53],"use":[55],"DRL":[57,94,114,129,165],"systems":[60],"with":[61,131],"limited":[62],"hardware":[63],"resources.":[64],"In":[65,96],"years,":[67],"pruning":[68,111,151],"have":[70],"demonstrated":[71],"considerable":[72],"reducing":[75],"redundancy":[77],"classification":[81],"tasks.":[82],"However,":[83],"existing":[84],"a":[88,118,136,147],"significant":[89],"performance":[90,107,133,177],"reduction":[91,108],"domain.":[95],"this":[97],"article,":[98],"we":[99,191],"develop":[100,192],"first":[102],"effective":[103],"solution":[104],"to":[105,127],"problem":[109],"domain,":[115],"establish":[117],"working":[119],"algorithm,":[120],"named":[121],"Policy":[122],"Pruning":[123],"Shrinking":[125],"(PoPS),":[126],"train":[128],"models":[130],"strong":[132,176],"while":[134],"achieving":[135],"compact":[137],"representation":[138],"DNN.":[141],"framework":[143],"is":[144],"based":[145],"on":[146],"novel":[148],"iterative":[149],"policy":[150],"shrinking":[153],"method":[154],"that":[155,173],"leverages":[156],"power":[158],"transfer":[160],"when":[162],"training":[163],"model.":[166],"We":[167],"present":[168],"an":[169,193],"extensive":[170],"experimental":[171],"study":[172],"demonstrates":[174],"PoPS":[179],"using":[180],"popular":[182],"Cartpole,":[183],"Lunar":[184],"Lander,":[185],"Pong,":[186],"Pacman":[188],"environments.":[189],"Finally,":[190],"open":[194],"source":[195],"software":[196],"benefit":[199],"researchers":[201],"developers":[203],"related":[205],"fields.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}