{"id":"https://openalex.org/W2963097726","doi":"https://doi.org/10.1609/aaai.v33i01.33014384","title":"The Utility of Sparse Representations for Control in Reinforcement Learning","display_name":"The Utility of Sparse Representations for Control in Reinforcement Learning","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2963097726","doi":"https://doi.org/10.1609/aaai.v33i01.33014384","mag":"2963097726"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33014384","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014384","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4349/4227","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4349/4227","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101890152","display_name":"Vincent Liu","orcid":"https://orcid.org/0000-0001-7683-208X"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Vincent Liu","raw_affiliation_strings":["University of Alberta"],"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021470452","display_name":"Raksha Kumaraswamy","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Raksha Kumaraswamy","raw_affiliation_strings":["University of Alberta"],"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102347070","display_name":"Lei Le","orcid":"https://orcid.org/0000-0002-0123-1586"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Le","raw_affiliation_strings":["Indiana University Bloomington"],"affiliations":[{"raw_affiliation_string":"Indiana University Bloomington","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101613484","display_name":"Martha White","orcid":"https://orcid.org/0000-0002-5356-2950"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Martha White","raw_affiliation_strings":["University of Alberta"],"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101890152"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":3.4108,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.93264781,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"33","issue":"01","first_page":"4384","last_page":"4391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9677000045776367,"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":0.9677000045776367,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9617000222206116,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9333999752998352,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8066389560699463},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.7086631059646606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6955090761184692},{"id":"https://openalex.org/keywords/neural-coding","display_name":"Neural coding","score":0.6761907339096069},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.6274722814559937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5831245183944702},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5523051023483276},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5009851455688477},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4750778079032898},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4441993236541748},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1408672332763672}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8066389560699463},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.7086631059646606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6955090761184692},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.6761907339096069},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.6274722814559937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5831245183944702},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5523051023483276},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5009851455688477},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4750778079032898},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4441993236541748},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1408672332763672},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v33i01.33014384","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014384","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4349/4227","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33014384","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014384","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4349/4227","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963097726.pdf","grobid_xml":"https://content.openalex.org/works/W2963097726.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W166862392","https://openalex.org/W1531103298","https://openalex.org/W1548867233","https://openalex.org/W1554576613","https://openalex.org/W1556929283","https://openalex.org/W1573706465","https://openalex.org/W1648730075","https://openalex.org/W1682403713","https://openalex.org/W2072599882","https://openalex.org/W2095705004","https://openalex.org/W2096765209","https://openalex.org/W2105728138","https://openalex.org/W2106884367","https://openalex.org/W2108665656","https://openalex.org/W2108838716","https://openalex.org/W2112447569","https://openalex.org/W2124175081","https://openalex.org/W2125138707","https://openalex.org/W2133257461","https://openalex.org/W2156387975","https://openalex.org/W2161278885","https://openalex.org/W2163922914","https://openalex.org/W2164724958","https://openalex.org/W2172174689","https://openalex.org/W2218318129","https://openalex.org/W2514813345","https://openalex.org/W2736341190","https://openalex.org/W2800142021","https://openalex.org/W2953139536","https://openalex.org/W2963394426","https://openalex.org/W2963644868","https://openalex.org/W4214717370","https://openalex.org/W4231109964","https://openalex.org/W4238276956","https://openalex.org/W4241004103","https://openalex.org/W4297799865","https://openalex.org/W6631708475","https://openalex.org/W6634210920","https://openalex.org/W6668502408","https://openalex.org/W6674201379","https://openalex.org/W6676231525","https://openalex.org/W6676419988","https://openalex.org/W6677916085","https://openalex.org/W6678757208","https://openalex.org/W6990768437"],"related_works":["https://openalex.org/W2890544631","https://openalex.org/W2067062989","https://openalex.org/W3004790527","https://openalex.org/W4205656132","https://openalex.org/W2998105788","https://openalex.org/W2539392819","https://openalex.org/W2111634407","https://openalex.org/W2783282829","https://openalex.org/W2579633471","https://openalex.org/W2203155458"],"abstract_inverted_index":{"We":[0,79,107,116,143],"investigate":[1],"sparse":[2,26,90,114,139,152,168],"representations":[3,11,30,169],"for":[4,31,85,105,164,170],"control":[5,46,60],"in":[6,15,20,58,138],"reinforcement":[7,21,171],"learning.":[8,172],"While":[9],"these":[10],"are":[12],"widely":[13],"used":[14],"computer":[16],"vision,":[17],"their":[18],"prevalence":[19],"learning":[22,44,63],"is":[23,77,87,129],"limited":[24],"to":[25,111,131,150],"coding":[27],"where":[28,123],"extracting":[29],"new":[32],"data":[33],"can":[34],"be":[35],"computationally":[36],"intensive.":[37],"Here,":[38],"we":[39],"begin":[40],"by":[41,156],"demonstrating":[42],"that":[43,72,82,88,136],"a":[45,50,53,65,69,133,145],"policy":[47],"incrementally":[48],"with":[49,64],"representation":[51,66,91],"from":[52,68],"standard":[54],"neural":[55,70],"network":[56,71],"fails":[57],"classic":[59],"domains,":[61],"whereas":[62],"obtained":[67],"has":[73],"sparsity":[74],"properties":[75],"enforced":[76],"effective.":[78],"provide":[80],"evidence":[81],"the":[83,89,118,124],"reason":[84],"this":[86],"provides":[92],"locality,":[93],"and":[94,99],"so":[95],"avoids":[96],"catastrophic":[97],"interference,":[98],"particularly":[100],"keeps":[101],"consistent,":[102],"stable":[103],"values":[104],"bootstrapping.":[106],"then":[108],"discuss":[109],"how":[110],"learn":[112],"such":[113],"representations.":[115],"explore":[117],"idea":[119],"of":[120,126],"Distributional":[121],"Regularizers,":[122],"activation":[125,140],"hidden":[127],"nodes":[128],"encouraged":[130],"match":[132],"particular":[134],"distribution":[135],"results":[137],"across":[141],"time.":[142],"identify":[144],"simple":[146],"but":[147],"effective":[148],"way":[149],"obtain":[151],"representations,":[153],"not":[154],"afforded":[155],"previously":[157],"proposed":[158],"strategies,":[159],"making":[160],"it":[161],"more":[162],"practical":[163],"further":[165],"investigation":[166],"into":[167]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}