{"id":"https://openalex.org/W4391936016","doi":"https://doi.org/10.1109/access.2024.3367002","title":"Pruning With Scaled Policy Constraints for Light-Weight Reinforcement Learning","display_name":"Pruning With Scaled Policy Constraints for Light-Weight Reinforcement Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391936016","doi":"https://doi.org/10.1109/access.2024.3367002"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3367002","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3367002","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10439169.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10439169.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039013553","display_name":"S.K. Park","orcid":"https://orcid.org/0009-0001-8568-5808"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seongmin Park","raw_affiliation_strings":["Department of Electronic Engineering, Hanyang University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0001-8568-5808","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695855","display_name":"Hyungmin Kim","orcid":"https://orcid.org/0000-0002-7626-4876"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]},{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyungmin Kim","raw_affiliation_strings":["Autonomous IoT Research Section, Electronics and Telecommunications Research Institute, Daejeon, South Korea","Department of Electronic Engineering, Hanyang University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous IoT Research Section, Electronics and Telecommunications Research Institute, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]},{"raw_affiliation_string":"Department of Electronic Engineering, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056296517","display_name":"Hyunhak Kim","orcid":"https://orcid.org/0000-0001-7013-0773"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]},{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunhak Kim","raw_affiliation_strings":["Autonomous IoT Research Section, Electronics and Telecommunications Research Institute, Daejeon, South Korea","Department of Electronic Engineering, Hanyang University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous IoT Research Section, Electronics and Telecommunications Research Institute, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]},{"raw_affiliation_string":"Department of Electronic Engineering, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078440061","display_name":"Jungwook Choi","orcid":"https://orcid.org/0000-0002-3075-8694"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jungwook Choi","raw_affiliation_strings":["Department of Electronic Engineering, Hanyang University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-3075-8694","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.4829,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56763051,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"12","issue":null,"first_page":"36055","last_page":"36065"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9972000122070312,"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/pruning","display_name":"Pruning","score":0.8603420257568359},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7780296802520752},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6964904069900513},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6953214406967163},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.4466606378555298},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40535587072372437},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3829575777053833}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.8603420257568359},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7780296802520752},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6964904069900513},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6953214406967163},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.4466606378555298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40535587072372437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3829575777053833},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3367002","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3367002","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10439169.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d7ab632960ac4a99995dacb1a51c8dae","is_oa":true,"landing_page_url":"https://doaj.org/article/d7ab632960ac4a99995dacb1a51c8dae","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 36055-36065 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3367002","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3367002","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10439169.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1822157532","display_name":null,"funder_award_id":"2020M3H2A1076786","funder_id":"https://openalex.org/F4320322030","funder_display_name":"Ministry of Science, ICT and Future Planning"},{"id":"https://openalex.org/G3544826714","display_name":null,"funder_award_id":"HY-201900000002966","funder_id":"https://openalex.org/F4320321142","funder_display_name":"Hanyang University"},{"id":"https://openalex.org/G412522711","display_name":null,"funder_award_id":"23ZR1100","funder_id":"https://openalex.org/F4320322093","funder_display_name":"Electronics and Telecommunications Research Institute"}],"funders":[{"id":"https://openalex.org/F4320321142","display_name":"Hanyang University","ror":"https://ror.org/046865y68"},{"id":"https://openalex.org/F4320322030","display_name":"Ministry of Science, ICT and Future Planning","ror":"https://ror.org/032e49973"},{"id":"https://openalex.org/F4320322093","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391936016.pdf","grobid_xml":"https://content.openalex.org/works/W4391936016.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2119144962","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2166302491","https://openalex.org/W2167340365","https://openalex.org/W2554302513","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2805003733","https://openalex.org/W2928560789","https://openalex.org/W2945146780","https://openalex.org/W2962851801","https://openalex.org/W2962890638","https://openalex.org/W2962965870","https://openalex.org/W2962977206","https://openalex.org/W2963363373","https://openalex.org/W2963864421","https://openalex.org/W2965862774","https://openalex.org/W2991355586","https://openalex.org/W2999204576","https://openalex.org/W3016525976","https://openalex.org/W3187908937","https://openalex.org/W3212876771","https://openalex.org/W4214717370","https://openalex.org/W4226053852","https://openalex.org/W4233840023","https://openalex.org/W4286900293","https://openalex.org/W4301501993","https://openalex.org/W4312690709","https://openalex.org/W4382318909","https://openalex.org/W6638018090","https://openalex.org/W6677580257","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6725543821","https://openalex.org/W6726275242","https://openalex.org/W6728155968","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6751979845","https://openalex.org/W6752963931","https://openalex.org/W6755015941","https://openalex.org/W6763704811","https://openalex.org/W6771270455","https://openalex.org/W6776601253","https://openalex.org/W6779265984","https://openalex.org/W6796589144","https://openalex.org/W6803524951","https://openalex.org/W6810580828","https://openalex.org/W6840899668"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"The":[0],"increasing":[1],"computational":[2,48,140,202],"demands":[3],"of":[4,105,158],"Deep":[5],"Reinforcement":[6],"Learning":[7],"(DRL)":[8],"models,":[9],"particularly":[10],"for":[11,39,47,96,247],"embedded":[12],"systems":[13],"in":[14,149,177,183,192],"autonomous":[15],"vehicles":[16],"and":[17,129,148,185,218,229,254],"drones,":[18],"present":[19],"significant":[20],"challenges":[21],"owing":[22],"to":[23,74,79],"their":[24],"extensive":[25],"neural":[26],"network":[27],"complexities.":[28],"Previous":[29],"DRL":[30,51,97],"compression":[31],"strategies":[32],"predominantly":[33],"focused":[34],"on":[35,60,144,204,211,223,234],"unstructured":[36],"pruning,":[37,108],"effective":[38],"reducing":[40],"model":[41,116],"size":[42],"but":[43],"requiring":[44],"specialized":[45],"hardware":[46],"acceleration.":[49],"Conversely,":[50],"models":[52],"with":[53,91,127,137,171,225,236],"structured":[54,87,107],"pruning":[55,71,88,111,122,169,182,191],"applied":[56],"can":[57],"be":[58],"accelerated":[59],"standard":[61,205],"hardware,":[62],"though":[63],"they":[64],"typically":[65],"encounter":[66],"performance":[67,103,119,164],"issues":[68],"at":[69,167,180,189],"higher":[70],"rates":[72,112],"due":[73],"structural":[75,131],"constraints.":[76],"In":[77],"response":[78],"these":[80],"challenges,":[81],"this":[82],"paper":[83],"introduces":[84],"an":[85],"advanced":[86],"methodology,":[89],"combined":[90],"scaled":[92],"policy":[93],"constraints":[94],"(SPC)":[95],"models.":[98],"Our":[99,161],"approach":[100,162,198],"overcomes":[101],"the":[102,145,156,212,232],"limitations":[104],"conventional":[106],"achieving":[109],"high":[110,168],"while":[113],"maintaining":[114],"robust":[115],"performance.":[117],"Enhanced":[118],"restoration":[120],"after":[121],"is":[123],"achieved":[124,219],"by":[125],"fine-tuning":[126],"SPC":[128],"applying":[130],"regularization,":[132],"thus":[133],"ensuring":[134],"efficient":[135],"decision-making":[136],"a":[138,150,174,220],"minimal":[139],"burden.":[141],"Extensive":[142],"evaluations":[143],"D4RL":[146,184],"benchmark":[147],"drone":[151,193],"control":[152,194],"simulation":[153],"environment":[154],"confirm":[155],"effectiveness":[157],"our":[159,197,209,244],"method.":[160],"maintains":[163],"integrity":[165],"even":[166],"rates,":[170],"less":[172],"than":[173],"2%":[175],"decrease":[176],"normalized":[178],"score":[179],"90%":[181],"preserving":[186],"cumulative":[187],"reward":[188],"87%":[190],"simulation.":[195],"Significantly,":[196],"also":[199],"enables":[200],"considerable":[201],"acceleration":[203],"hardware.":[206],"We":[207],"implemented":[208],"method":[210],"NVIDIA":[213,226,237],"Jetson":[214],"Xavier":[215],"NX":[216],"board":[217],"2.5-fold":[221],"speed-up":[222,233],"devices":[224],"Volta":[227],"GPUs":[228],"over":[230],"double":[231],"those":[235],"Carmel":[238],"ARMv8.2":[239],"CPUs.":[240],"These":[241],"outcomes":[242],"highlight":[243],"method\u2019s":[245],"suitability":[246],"real-time,":[248],"resource-constrained":[249],"applications,":[250],"demonstrating":[251],"its":[252],"practicality":[253],"efficiency.":[255]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}