{"id":"https://openalex.org/W4284707721","doi":"https://doi.org/10.1109/isorc52572.2022.9812837","title":"LRP-based Policy Pruning and Distillation of Reinforcement Learning Agents for Embedded Systems","display_name":"LRP-based Policy Pruning and Distillation of Reinforcement Learning Agents for Embedded Systems","publication_year":2022,"publication_date":"2022-05-17","ids":{"openalex":"https://openalex.org/W4284707721","doi":"https://doi.org/10.1109/isorc52572.2022.9812837"},"language":"en","primary_location":{"id":"doi:10.1109/isorc52572.2022.9812837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isorc52572.2022.9812837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 25th International Symposium On Real-Time Distributed Computing (ISORC)","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/A5101426309","display_name":"Rui Xu","orcid":"https://orcid.org/0000-0001-6891-8027"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Xu","raw_affiliation_strings":["Nanjing University of Science and Technology,School of Computer Science and Engineering,Nanjing,China","School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025159531","display_name":"Siyu Luan","orcid":"https://orcid.org/0000-0002-6955-4445"},"institutions":[{"id":"https://openalex.org/I90267481","display_name":"Ume\u00e5 University","ror":"https://ror.org/05kb8h459","country_code":"SE","type":"education","lineage":["https://openalex.org/I90267481"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Siyu Luan","raw_affiliation_strings":["Umeå University,Department of Applied Physics and Electronics,Umeå,Sweden"],"affiliations":[{"raw_affiliation_string":"Umeå University,Department of Applied Physics and Electronics,Umeå,Sweden","institution_ids":["https://openalex.org/I90267481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029808393","display_name":"Zonghua Gu","orcid":"https://orcid.org/0000-0003-4228-2774"},"institutions":[{"id":"https://openalex.org/I90267481","display_name":"Ume\u00e5 University","ror":"https://ror.org/05kb8h459","country_code":"SE","type":"education","lineage":["https://openalex.org/I90267481"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Zonghua Gu","raw_affiliation_strings":["Umeå University,Department of Applied Physics and Electronics,Umeå,Sweden"],"affiliations":[{"raw_affiliation_string":"Umeå University,Department of Applied Physics and Electronics,Umeå,Sweden","institution_ids":["https://openalex.org/I90267481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011502544","display_name":"Qingling Zhao","orcid":"https://orcid.org/0000-0003-4880-7148"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingling Zhao","raw_affiliation_strings":["Nanjing University of Science and Technology,School of Computer Science and Engineering,Nanjing,China","School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100389329","display_name":"Gang Chen","orcid":"https://orcid.org/0000-0003-4234-1359"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Chen","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China","School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101426309"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":0.9283,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78413972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"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":0.9934999942779541,"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":0.9934999942779541,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9793999791145325,"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.9585999846458435,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.8809677362442017},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7993487119674683},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.7583709955215454},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6744440793991089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5489044189453125},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4437279999256134},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44101038575172424},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.13304251432418823},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.09695816040039062},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.06078490614891052}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8809677362442017},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7993487119674683},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.7583709955215454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6744440793991089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5489044189453125},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4437279999256134},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44101038575172424},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.13304251432418823},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.09695816040039062},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.06078490614891052},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isorc52572.2022.9812837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isorc52572.2022.9812837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 25th International Symposium On Real-Time Distributed Computing (ISORC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4099999964237213}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1787224781","https://openalex.org/W1821462560","https://openalex.org/W1931877416","https://openalex.org/W2046376809","https://openalex.org/W2119144962","https://openalex.org/W2263410234","https://openalex.org/W2571808120","https://openalex.org/W2584322061","https://openalex.org/W2701971652","https://openalex.org/W2707890836","https://openalex.org/W2746553466","https://openalex.org/W2803740478","https://openalex.org/W2808168148","https://openalex.org/W2887286714","https://openalex.org/W2914731160","https://openalex.org/W2973136764","https://openalex.org/W2994881943","https://openalex.org/W3012561096","https://openalex.org/W3047831953","https://openalex.org/W3184606595","https://openalex.org/W4211021930","https://openalex.org/W4298845604","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6638523607","https://openalex.org/W6640174482","https://openalex.org/W6677580257","https://openalex.org/W6732511369","https://openalex.org/W6732837357","https://openalex.org/W6739917289","https://openalex.org/W6740114376","https://openalex.org/W6748440607","https://openalex.org/W6751398007","https://openalex.org/W6759225949"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Reinforcement":[0,17],"Learning":[1,18],"(RL)":[2],"is":[3,68,147],"an":[4,98],"effective":[5,148],"approach":[6,146],"to":[7,70,79,118],"developing":[8],"control":[9],"policies":[10],"by":[11,101,107],"maximizing":[12],"the":[13,72,76,94,103,122,126],"agent\u2019s":[14],"reward.":[15],"Deep":[16,21],"(DRL)":[19],"uses":[20],"Neural":[22],"Networks":[23],"(DNNs)":[24],"for":[25,114],"function":[26],"approximation":[27],"in":[28,35,125,149],"RL,":[29],"and":[30,45,83,120,153],"has":[31],"achieved":[32],"tremendous":[33],"success":[34],"recent":[36],"years.":[37],"Large":[38],"DNNs":[39],"often":[40],"incur":[41],"significant":[42],"memory":[43,82],"size":[44,152],"computational":[46],"overheads,":[47],"which":[48],"greatly":[49],"impedes":[50],"their":[51],"deployment":[52,58],"into":[53],"resource-constrained":[54],"embedded":[55,65],"systems.":[56],"For":[57],"of":[59,75,93,97,156],"a":[60,112],"trained":[61],"RL":[62,77,99,157],"agent":[63,78,100],"on":[64,138],"systems,":[66],"it":[67],"necessary":[69],"compress":[71],"Policy":[73,95,127,133],"Network":[74,96],"improve":[80],"its":[81],"computation":[84],"efficiency.":[85],"In":[86],"this":[87],"paper,":[88],"we":[89],"perform":[90],"model":[91,151],"compression":[92],"leveraging":[102],"relevance":[104],"scores":[105],"computed":[106],"Layer-wise":[108],"Relevance":[109],"Propagation":[110],"(LRP),":[111],"technique":[113],"Explainable":[115],"AI":[116],"(XAI),":[117],"rank":[119],"prune":[121],"convolutional":[123],"filters":[124],"Network,":[128],"combined":[129],"with":[130,132],"fine-tuning":[131],"Distillation.":[134],"Performance":[135],"evaluation":[136],"based":[137],"several":[139],"Atari":[140],"games":[141],"indicates":[142],"that":[143],"our":[144],"proposed":[145],"reducing":[150],"inference":[154],"time":[155],"agents.":[158]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}