{"id":"https://openalex.org/W7151503625","doi":"https://doi.org/10.1109/icmla66185.2025.00035","title":"Sparse RNNs in Reinforcement Learning Applications","display_name":"Sparse RNNs in Reinforcement Learning Applications","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7151503625","doi":"https://doi.org/10.1109/icmla66185.2025.00035"},"language":null,"primary_location":{"id":"doi:10.1109/icmla66185.2025.00035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","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/A5094188546","display_name":"Quincy Hershey","orcid":"https://orcid.org/0009-0000-8762-3646"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Quincy Hershey","raw_affiliation_strings":["Worcester Polytechnic Institute,Data Science,Worcester,United States"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute,Data Science,Worcester,United States","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027655988","display_name":"Randy Paffenroth","orcid":"https://orcid.org/0000-0002-4823-1348"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Randy Paffenroth","raw_affiliation_strings":["Worcester Polytechnic Institute,Mathematical Sciences, Computer Science, and Data Science,Worcester,United States"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute,Mathematical Sciences, Computer Science, and Data Science,Worcester,United States","institution_ids":["https://openalex.org/I107077323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5094188546"],"corresponding_institution_ids":["https://openalex.org/I107077323"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87289807,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"230","last_page":"237"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.3846000134944916,"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":0.3846000134944916,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.07029999792575836,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.031300000846385956,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.76910001039505},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.630299985408783},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5192999839782715},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4948999881744385},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.4296000003814697},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4097000062465668},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.3847000002861023}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.76910001039505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6844000220298767},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.630299985408783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5823000073432922},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5192999839782715},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4948999881744385},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45010000467300415},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.3847000002861023},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.2736000120639801},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C2777299769","wikidata":"https://www.wikidata.org/wiki/Q3707858","display_name":"Type (biology)","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C2988886741","wikidata":"https://www.wikidata.org/wiki/Q25304494","display_name":"Dictionary learning","level":3,"score":0.2540999948978424},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmla66185.2025.00035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1604264128","https://openalex.org/W2064675550","https://openalex.org/W2107726111","https://openalex.org/W2293634267","https://openalex.org/W2498979687","https://openalex.org/W2885195348","https://openalex.org/W2963411833","https://openalex.org/W2970848711","https://openalex.org/W3121852482","https://openalex.org/W4302493448","https://openalex.org/W4392942293"],"related_works":[],"abstract_inverted_index":{"Herein,":[0],"we":[1],"explore":[2],"the":[3,40,45,50,57,85,121,136],"use":[4],"of":[5,36,42,68,73,82,123,125,135],"sparse":[6,76,111,133],"Recurrent":[7],"Neural":[8],"Network":[9],"(RNN)":[10],"architectures":[11],"in":[12,29,139],"Reinforcement":[13],"Learning":[14],"(RL)":[15],"applications.":[16],"We":[17,31],"demonstrate":[18],"that":[19,48,67,132],"sparsely":[20],"parameterized":[21],"weight":[22,46,59,86],"matrices":[23,47],"offer":[24,141],"advantages":[25],"for":[26],"model":[27,51,148],"stability":[28],"training.":[30],"introduce":[32],"a":[33],"novel":[34],"method":[35],"hyper-parameterization":[37],"by":[38],"varying":[39,54,80],"degree":[41],"sparsity":[43,55,83],"within":[44],"form":[49],"architecture.":[52],"With":[53],"among":[56,84],"trainable":[58,126,137],"matrices,":[60,87],"RNN":[61],"performance":[62,143],"improves":[63],"significantly":[64],"and":[65],"surpasses":[66],"RNNs":[69,112,140],"with":[70],"uniform":[71],"levels":[72,81],"sparsity.":[74],"Additionally,":[75],"RNNs,":[77],"which":[78],"utilize":[79],"are":[88,113],"shown":[89,114],"to":[90,115],"outperform":[91],"competing":[92],"models":[93],"on":[94,120],"RL":[95],"tasks,":[96],"including":[97],"those":[98],"traditionally":[99],"viewed":[100],"as":[101,104],"superior,":[102],"such":[103],"Long-Short":[105],"Term":[106],"Memory":[107],"(LSTM)":[108],"models.":[109],"Furthermore,":[110],"perform":[116],"more":[117],"efficiently":[118],"measured":[119],"basis":[122],"number":[124],"weights.":[127],"Overall,":[128],"this":[129],"research":[130],"demonstrates":[131],"parameterizations":[134],"weights":[138],"clear":[142],"benefits":[144],"while":[145],"also":[146],"improving":[147],"stability.":[149]},"counts_by_year":[],"updated_date":"2026-04-09T06:08:40.794217","created_date":"2026-04-08T00:00:00"}