{"id":"https://openalex.org/W4285600354","doi":"https://doi.org/10.24963/ijcai.2022/477","title":"Dynamic Sparse Training for Deep Reinforcement Learning","display_name":"Dynamic Sparse Training for Deep Reinforcement Learning","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285600354","doi":"https://doi.org/10.24963/ijcai.2022/477"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/477","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/477","pdf_url":"https://www.ijcai.org/proceedings/2022/0477.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0477.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021535037","display_name":"Ghada Sokar","orcid":null},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ghada Sokar","raw_affiliation_strings":["Eindhoven University of Technology (TU/e)","Eindhoven University of Technology, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology (TU/e)","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Eindhoven University of Technology, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027401676","display_name":"Elena Mocanu","orcid":"https://orcid.org/0000-0002-0856-579X"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Elena Mocanu","raw_affiliation_strings":["University of Twente","University of Twente, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Twente","institution_ids":["https://openalex.org/I94624287"]},{"raw_affiliation_string":"University of Twente, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011045254","display_name":"Decebal Constantin Mocanu","orcid":"https://orcid.org/0000-0002-5636-7683"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]},{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Decebal Constantin Mocanu","raw_affiliation_strings":["Eindhoven University of Technology","University of Twente,","Eindhoven University of Technology, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"University of Twente,","institution_ids":["https://openalex.org/I94624287"]},{"raw_affiliation_string":"Eindhoven University of Technology, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022601535","display_name":"Mykola Pechenizkiy","orcid":"https://orcid.org/0000-0003-4955-0743"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]},{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mykola Pechenizkiy","raw_affiliation_strings":["Eindhoven University of Technology (TU/e)","University of Twente, The Netherlands","Eindhoven University of Technology, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology (TU/e)","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"University of Twente, The Netherlands","institution_ids":["https://openalex.org/I94624287"]},{"raw_affiliation_string":"Eindhoven University of Technology, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001594330","display_name":"Peter Stone","orcid":"https://orcid.org/0000-0002-6795-420X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Stone","raw_affiliation_strings":["The University of Texas at Austin, Sony AI","The University of Texas at Austin, Sony AI, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Sony AI","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"The University of Texas at Austin, Sony AI, United States","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3437","last_page":"3443"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9887999892234802,"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9819999933242798,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8034555912017822},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7902277708053589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5860747694969177},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.5574434995651245},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.531832754611969},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5274836421012878},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4896838963031769},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4866231381893158},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4632972180843353},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.4564284682273865},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.4275131821632385},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4126926362514496},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4115634858608246},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.1271006464958191}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8034555912017822},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7902277708053589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5860747694969177},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.5574434995651245},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.531832754611969},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5274836421012878},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4896838963031769},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4866231381893158},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4632972180843353},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.4564284682273865},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.4275131821632385},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4126926362514496},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4115634858608246},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.1271006464958191},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"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/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.24963/ijcai.2022/477","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/477","pdf_url":"https://www.ijcai.org/proceedings/2022/0477.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/b22bac78-c5e7-42d4-90bb-3617291ecc15","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/b22bac78-c5e7-42d4-90bb-3617291ecc15","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sokar, G A Z N, Mocanu, E, Mocanu, D C, Pechenizkiy, M & Stone, P 2022, Dynamic Sparse Training for Deep Reinforcement Learning. in L De Raedt (ed.), Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022. pp. 3437-3443, 31st International Joint Conference on Artificial Intelligence, IJCAI 2022, Vienna, Austria, 23/07/18. https://doi.org/10.24963/ijcai.2022/477","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arXiv.org:2106.04217","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.04217","pdf_url":"https://arxiv.org/pdf/2106.04217","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":"","raw_type":"text"},{"id":"pmh:oai:ris.utwente.nl:publications/b22bac78-c5e7-42d4-90bb-3617291ecc15","is_oa":false,"landing_page_url":"https://github.com/GhadaSokar/Dynamic-Sparse-Training-for-Deep-Reinforcement-Learning","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:ut:oai:ris.utwente.nl:publications/a865aa1a-b5a9-4283-ab31-e3ef4ff03d71","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/a865aa1a-b5a9-4283-ab31-e3ef4ff03d71","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/workingpaper"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/477","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/477","pdf_url":"https://www.ijcai.org/proceedings/2022/0477.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285600354.pdf","grobid_xml":"https://content.openalex.org/works/W4285600354.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2066251678","https://openalex.org/W2111935653","https://openalex.org/W2116339921","https://openalex.org/W2120181489","https://openalex.org/W2606722458","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2805003733","https://openalex.org/W2902625698","https://openalex.org/W2904246096","https://openalex.org/W2948130861","https://openalex.org/W2949413532","https://openalex.org/W2952899695","https://openalex.org/W2978696242","https://openalex.org/W2982316857","https://openalex.org/W2990844796","https://openalex.org/W2999204576","https://openalex.org/W3015921997","https://openalex.org/W3038428716","https://openalex.org/W3042228527","https://openalex.org/W3093426589","https://openalex.org/W3101584733","https://openalex.org/W3107554570","https://openalex.org/W3121197820","https://openalex.org/W3123338478","https://openalex.org/W3142570770","https://openalex.org/W3144538040","https://openalex.org/W4287123848","https://openalex.org/W4287185454","https://openalex.org/W4287363917"],"related_works":["https://openalex.org/W2475116013","https://openalex.org/W2770018148","https://openalex.org/W2358308169","https://openalex.org/W2385135707","https://openalex.org/W2140315382","https://openalex.org/W2059109728","https://openalex.org/W322691623","https://openalex.org/W2494989134","https://openalex.org/W2509444723","https://openalex.org/W2004958254"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,69],"learning":[2,37,70,131],"(DRL)":[3],"agents":[4,40,108,140],"are":[5,34],"trained":[6],"through":[7],"trial-and-error":[8],"interactions":[9],"with":[10,141],"the":[11,59,73,92,113,118,136,145],"environment.":[12],"This":[13],"leads":[14],"to":[15,24,71,91],"a":[16,62,80,129],"long":[17],"training":[18,65,74,146],"time":[19,61],"for":[20,58,67],"dense":[21,115,139],"neural":[22,82],"networks":[23],"achieve":[25,109],"good":[26],"performance.":[27],"Hence,":[28],"prohibitive":[29],"computation":[30],"and":[31,86,121,127],"memory":[32],"resources":[33],"consumed.":[35],"Recently,":[36],"efficient":[38],"DRL":[39],"has":[41],"received":[42],"increasing":[43],"attention.":[44],"Yet,":[45],"current":[46],"methods":[47],"focus":[48],"on":[49,99],"accelerating":[50],"inference":[51],"time.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"introduce":[57],"first":[60],"dynamic":[63,106],"sparse":[64,81,107],"approach":[66,78],"deep":[68],"accelerate":[72],"process.":[75],"The":[76],"proposed":[77],"trains":[79],"network":[83],"from":[84],"scratch":[85],"dynamically":[87],"adapts":[88],"its":[89],"topology":[90],"changing":[93],"data":[94],"distribution":[95],"during":[96],"training.":[97],"Experiments":[98],"continuous":[100],"control":[101],"tasks":[102],"show":[103],"that":[104,133],"our":[105],"higher":[110],"performance":[111,137],"than":[112],"equivalent":[114],"methods,":[116],"reduce":[117],"parameter":[119],"count":[120],"floating-point":[122],"operations":[123],"(FLOPs)":[124],"by":[125],"50%,":[126],"have":[128],"faster":[130],"speed":[132],"enables":[134],"reaching":[135],"of":[138],"40\u221250%":[142],"reduction":[143],"in":[144],"steps.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}