{"id":"https://openalex.org/W395196838","doi":null,"title":"Sparse value function approximation for reinforcement learning","display_name":"Sparse value function approximation for reinforcement learning","alternate_titles":[],"publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W395196838","mag":"395196838"},"language":"en","primary_location":{"id":"pmh:oai:dukespace.lib.duke.edu:10161/7250","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10161/7250","pdf_url":null,"source":{"id":"https://openalex.org/S4306400687","display_name":"DukeSpace (Duke University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I170897317","host_organization_name":"Duke University","host_organization_lineage":["https://openalex.org/I170897317"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},"parent_works":[],"lineage":["https://openalex.org/W395196838"],"child_works_count":0,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10161/7250","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109839104","display_name":"Ronald Parr","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Ronald Parr","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060178852","display_name":"Christopher Painter-Wakefield","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Christopher Painter-Wakefield","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"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"}},{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.7459999918937683},{"id":"https://openalex.org/keywords/l1-regularization","display_name":"L1 regularization","score":0.9909999966621399},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"temporal difference learning","score":0.8899999856948853},{"id":"https://openalex.org/keywords/fixed-point-convergence","display_name":"fixed point convergence","score":0.6100000143051147},{"id":"https://openalex.org/keywords/policy-optimization","display_name":"policy optimization","score":0.6949999928474426},{"id":"https://openalex.org/keywords/orthogonal-matching-pursuit","display_name":"orthogonal matching pursuit","score":0.8289999961853027},{"id":"https://openalex.org/keywords/sparse-signal-recovery","display_name":"sparse signal recovery","score":0.9539999961853027},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7260000109672546}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7279508709907532},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.6549785137176514},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5876584053039551},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5701544284820557},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.5632803440093994},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5597453117370605},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.5532019138336182},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4917342960834503},{"id":"https://openalex.org/C61445026","wikidata":"https://www.wikidata.org/wiki/Q217608","display_name":"Fixed point","level":2,"score":0.48026442527770996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47069454193115234},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4602595269680023},{"id":"https://openalex.org/C160824197","wikidata":"https://www.wikidata.org/wiki/Q2071054","display_name":"Linear approximation","level":3,"score":0.4198454022407532},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.41854605078697205},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.393435537815094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3649700880050659},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.22478634119033813},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.1301366686820984},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12831050157546997},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:dukespace.lib.duke.edu:10161/7250","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10161/7250","pdf_url":null,"source":{"id":"https://openalex.org/S4306400687","display_name":"DukeSpace (Duke University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I170897317","host_organization_name":"Duke University","host_organization_lineage":["https://openalex.org/I170897317"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},{"id":"mag:395196838","doi":null,"is_oa":false,"landing_page_url":"https://dukespace.lib.duke.edu/dspace/bitstream/10161/7250/1/PainterWakefield_duke_0066D_11956.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:dukespace.lib.duke.edu:10161/7250","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10161/7250","pdf_url":null,"source":{"id":"https://openalex.org/S4306400687","display_name":"DukeSpace (Duke University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I170897317","host_organization_name":"Duke University","host_organization_lineage":["https://openalex.org/I170897317"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2290138457","display_name":"Collaborative: RI: Feature Discovery and Benchmarks for Exportable Reinforcement Learning","funder_award_id":"0713435","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3002304478","display_name":"CAREER:  Observing to Plan - Planning to Observe","funder_award_id":"0546709","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3847338926","display_name":"EAGER: IIS: RI: Learning in Continuous and High Dimensional Action Spaces","funder_award_id":"1147641","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5078493187","display_name":"RI: Small: Non-parametric Approximate Dynamic Programming for Continuous Domains","funder_award_id":"1218931","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7976467478","display_name":"Prediction and Planning:   Bridging the Gap","funder_award_id":"0209088","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W395196838.pdf","grobid_xml":"https://content.openalex.org/works/W395196838.grobid-xml"},"referenced_works_count":68,"referenced_works":["https://openalex.org/W594357522","https://openalex.org/W1460549585","https://openalex.org/W1487444668","https://openalex.org/W1505731132","https://openalex.org/W1509335638","https://openalex.org/W1511421254","https://openalex.org/W1512407760","https://openalex.org/W1547105496","https://openalex.org/W1576452626","https://openalex.org/W1597303641","https://openalex.org/W1646707810","https://openalex.org/W1745373831","https://openalex.org/W1904705466","https://openalex.org/W1980266375","https://openalex.org/W1994616650","https://openalex.org/W1998172110","https://openalex.org/W2009702064","https://openalex.org/W2011233848","https://openalex.org/W2045220410","https://openalex.org/W2046513829","https://openalex.org/W2062102668","https://openalex.org/W2063978378","https://openalex.org/W2071983464","https://openalex.org/W2072931156","https://openalex.org/W2078204800","https://openalex.org/W2100677568","https://openalex.org/W2108430473","https://openalex.org/W2110486110","https://openalex.org/W2112264645","https://openalex.org/W2115706991","https://openalex.org/W2116148865","https://openalex.org/W2118838680","https://openalex.org/W2119667497","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2122825543","https://openalex.org/W2123979492","https://openalex.org/W2125074935","https://openalex.org/W2128659236","https://openalex.org/W2129570755","https://openalex.org/W2130005627","https://openalex.org/W2132351269","https://openalex.org/W2132849848","https://openalex.org/W2135046866","https://openalex.org/W2137466452","https://openalex.org/W2138326839","https://openalex.org/W2147329339","https://openalex.org/W2151268438","https://openalex.org/W2151693816","https://openalex.org/W2153039919","https://openalex.org/W2158738729","https://openalex.org/W2158883409","https://openalex.org/W2158940042","https://openalex.org/W2161795906","https://openalex.org/W2164301055","https://openalex.org/W2167840144","https://openalex.org/W2170419304","https://openalex.org/W2188393917","https://openalex.org/W2200611301","https://openalex.org/W2944207242","https://openalex.org/W3007702476","https://openalex.org/W3011120880","https://openalex.org/W3022380717","https://openalex.org/W3139377883","https://openalex.org/W4301621763","https://openalex.org/W7014610195","https://openalex.org/W7095430823","https://openalex.org/W7098499361"],"related_works":["https://openalex.org/W84874842","https://openalex.org/W79486244","https://openalex.org/W7101153997","https://openalex.org/W3119408560","https://openalex.org/W2891364703","https://openalex.org/W2112264645","https://openalex.org/W2167840144","https://openalex.org/W7099613535","https://openalex.org/W2110158343","https://openalex.org/W1721038333"],"abstract_inverted_index":{"A":[0],"key":[1],"component":[2],"of":[3,12,20,32,39,79,101,107,111,155,172,190,197,309,323,327,346,350,361],"many":[4,322],"reinforcement":[5,85],"learning":[6,48,125,130,282],"(RL)":[7],"algorithms":[8,320,371],"is":[9,26,42,94,185,288],"the":[10,13,37,49,67,77,95,98,105,108,112,127,149,173,179,191,195,198,203,235,262,324,328,347,386,411],"approximation":[11,23,83,113,167,423],"value":[14,50,81,231,281],"function.":[15],"The":[16,157,253,285,369],"design":[17],"and":[18,28,61,176,283,374,425],"selection":[19,41,69],"features":[21,60],"for":[22,84,89],"in":[24,47,76,97,126,293,338,390,422],"RL":[25],"crucial,":[27],"an":[29,139,164,186],"ongoing":[30],"area":[31,78],"research.":[33],"One":[34,87],"approach":[35,118,304],"to":[36,43,57,122,163,200,202,225,241,261,275,290,305,367,395],"problem":[38],"feature":[40,68,412],"apply":[44],"sparsity-inducing":[45],"techniques":[46],"function":[51,82,100,354],"approximation;":[52],"such":[53],"sparse":[54,80,91,208,230,280,306,352,397],"methods":[55,420],"tend":[56],"select":[58],"relevant":[59],"ignore":[62],"irrelevant":[63],"features,":[64],"thus":[65],"automating":[66],"process.":[70],"This":[71,115],"dissertation":[72],"describes":[73],"three":[74],"contributions":[75],"learning.":[86,219,232],"method":[88],"obtaining":[90],"linear":[92,152,182,216,238],"approximations":[93],"inclusion":[96],"objective":[99],"a":[102,207,243,248,258,276,311,351],"penalty":[103],"on":[104,344,410,427],"sum":[106],"absolute":[109],"values":[110],"weights.":[114],"L1":[116,150,180,236,329,379],"regularization":[117,330],"was":[119],"first":[120,135],"applied":[121,366],"temporal":[123,217],"difference":[124,218],"LARS-inspired,":[128],"batch":[129],"algorithm":[131,175,199,278,287,313],"LARS-TD.":[132,156,299],"In":[133],"our":[134],"contribution,":[136],"we":[137,301],"define":[138],"iterative":[140,158],"update":[141,159],"equation":[142],"which":[143,264,391],"has":[144],"as":[145,267],"its":[146,270],"fixed":[147,153,183,188,204,239,251,255],"point":[148,154,184,189,240,256],"regularized":[151,181,237,380],"gives":[160],"rise":[161,274],"naturally":[162],"online":[165,174],"stochastic":[166],"algorithm.":[168,192],"We":[169,193,233,358,382],"prove":[170],"convergence":[171],"show":[177],"that":[178,308,314,384],"equilibrium":[187],"demonstrate":[194,383],"ability":[196],"converge":[201],"point,":[205],"yielding":[206],"solution":[209],"with":[210,229,295,377],"modestly":[211],"better":[212],"performance":[213,294],"than":[214],"unregularized":[215],"Our":[220],"second":[221],"contribution":[222],"extends":[223],"LARS-TD":[224,265],"integrate":[226],"policy":[227,296],"optimization":[228],"extend":[234],"include":[242],"maximum":[244],"over":[245],"policies,":[246],"defining":[247],"new,":[249],"\"greedy\"":[250],"point.":[252],"greedy":[254],"adds":[257,316],"new":[259,277,286,317],"invariant":[260],"set":[263],"maintains":[266],"it":[268],"traverses":[269],"homotopy":[271],"path,":[272],"giving":[273],"integrating":[279],"optimization.":[284],"demonstrated":[289],"be":[291],"similar":[292],"iteration":[297],"using":[298,310],"Finally,":[300],"consider":[302,359],"another":[303,415],"learning,":[307],"simple":[312],"greedily":[315],"features.":[318],"Such":[319],"have":[321],"good":[325],"properties":[326],"methods,":[331],"while":[332,414],"also":[333],"being":[334],"extremely":[335],"efficient":[336],"and,":[337],"some":[339],"cases,":[340],"allowing":[341],"theoretical":[342,405],"guarantees":[343,406],"recovery":[345,398],"true":[348],"form":[349],"target":[353],"from":[355],"sampled":[356],"data.":[357],"variants":[360],"orthogonal":[362],"matching":[363],"pursuit":[364],"(OMP)":[365],"RL.":[368],"resulting":[370],"are":[372],"analyzed":[373],"compared":[375],"experimentally":[376],"existing":[378],"approaches.":[381],"perhaps":[385],"most":[387],"natural":[388],"scenario":[389],"one":[392,401],"might":[393],"hope":[394],"achieve":[396],"fails;":[399],"however,":[400],"variant":[402,416],"provides":[403],"promising":[404],"under":[407],"certain":[408],"assumptions":[409],"dictionary":[413],"empirically":[417],"outperforms":[418],"prior":[419],"both":[421],"accuracy":[424],"efficiency":[426],"several":[428],"benchmark":[429],"problems.":[430]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W395196838","counts_by_year":[],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2016-06-24T00:00:00"}
