{"id":"https://openalex.org/W3025837736","doi":"https://doi.org/10.1109/tac.2020.3029315","title":"Policy Evaluation in Continuous MDPs With Efficient Kernelized Gradient Temporal Difference","display_name":"Policy Evaluation in Continuous MDPs With Efficient Kernelized Gradient Temporal Difference","publication_year":2020,"publication_date":"2020-10-07","ids":{"openalex":"https://openalex.org/W3025837736","doi":"https://doi.org/10.1109/tac.2020.3029315","mag":"3025837736"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2020.3029315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2020.3029315","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1709.04221","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025896653","display_name":"Alec Koppel","orcid":"https://orcid.org/0000-0003-2447-2873"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alec Koppel","raw_affiliation_strings":["Computational and Information Sciences Directorate, U.S. Army Research Laboratory, Adelphi, MD, USA","#N#               * University of Pennsylvania"],"raw_orcid":"https://orcid.org/0000-0003-2447-2873","affiliations":[{"raw_affiliation_string":"Computational and Information Sciences Directorate, U.S. Army Research Laboratory, Adelphi, MD, USA","institution_ids":["https://openalex.org/I166416128"]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":["https://openalex.org/I36788626","https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060981901","display_name":"Garrett Warnell","orcid":"https://orcid.org/0000-0003-3846-8787"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Garrett Warnell","raw_affiliation_strings":["Computational and Information Sciences Directorate, U.S. Army Research Laboratory, Adelphi, MD, USA","Computational and Information Sciences Directorate, U.S. Army Research Laboratory, Adelphi, MD, USA#TAB#"],"raw_orcid":"https://orcid.org/0000-0003-3846-8787","affiliations":[{"raw_affiliation_string":"Computational and Information Sciences Directorate, U.S. Army Research Laboratory, Adelphi, MD, USA","institution_ids":["https://openalex.org/I166416128"]},{"raw_affiliation_string":"Computational and Information Sciences Directorate, U.S. Army Research Laboratory, Adelphi, MD, USA#TAB#","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013003113","display_name":"Ethan Stump","orcid":"https://orcid.org/0000-0002-0119-2169"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ethan Stump","raw_affiliation_strings":["Computational and Information Sciences Directorate, U.S. Army Research Laboratory, Adelphi, MD, USA","Computational and Information Sciences Directorate, U.S. Army Research Laboratory, Adelphi, MD, USA#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-0119-2169","affiliations":[{"raw_affiliation_string":"Computational and Information Sciences Directorate, U.S. Army Research Laboratory, Adelphi, MD, USA","institution_ids":["https://openalex.org/I166416128"]},{"raw_affiliation_string":"Computational and Information Sciences Directorate, U.S. Army Research Laboratory, Adelphi, MD, USA#TAB#","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"middle","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":["Department of Computer Science, University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-6795-420X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078862959","display_name":"Alejandro Ribeiro","orcid":"https://orcid.org/0000-0003-4230-9906"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]},{"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":"Alejandro Ribeiro","raw_affiliation_strings":["Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA","University of Texas at Austin"],"raw_orcid":"https://orcid.org/0000-0003-4230-9906","affiliations":[{"raw_affiliation_string":"Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1343,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57063991,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"66","issue":"4","first_page":"1856","last_page":"1863"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996999979019165,"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":0.996999979019165,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9884999990463257,"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/bellman-equation","display_name":"Bellman equation","score":0.6110474467277527},{"id":"https://openalex.org/keywords/reproducing-kernel-hilbert-space","display_name":"Reproducing kernel Hilbert space","score":0.6077961325645447},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.6023169755935669},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5674289464950562},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5301918387413025},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.4930667579174042},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4863441586494446},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.47955796122550964},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.47755250334739685},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4649580419063568},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4609909653663635},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4535154402256012},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.4310801029205322},{"id":"https://openalex.org/keywords/hilbert-space","display_name":"Hilbert space","score":0.38067126274108887},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.35213762521743774},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2920474410057068},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19744956493377686},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.09972548484802246},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09731999039649963},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.08784151077270508}],"concepts":[{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6110474467277527},{"id":"https://openalex.org/C80884492","wikidata":"https://www.wikidata.org/wiki/Q3345678","display_name":"Reproducing kernel Hilbert space","level":3,"score":0.6077961325645447},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6023169755935669},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5674289464950562},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5301918387413025},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.4930667579174042},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4863441586494446},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.47955796122550964},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.47755250334739685},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4649580419063568},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4609909653663635},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4535154402256012},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.4310801029205322},{"id":"https://openalex.org/C62799726","wikidata":"https://www.wikidata.org/wiki/Q190056","display_name":"Hilbert space","level":2,"score":0.38067126274108887},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35213762521743774},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2920474410057068},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19744956493377686},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.09972548484802246},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09731999039649963},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.08784151077270508},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tac.2020.3029315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2020.3029315","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1709.04221","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1709.04221","pdf_url":"https://arxiv.org/pdf/1709.04221","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":null,"raw_type":"text"},{"id":"mag:3025837736","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1709.04221","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1709.04221","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1709.04221","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1709.04221","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1709.04221","pdf_url":"https://arxiv.org/pdf/1709.04221","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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W1494085563","https://openalex.org/W1514587017","https://openalex.org/W1515878031","https://openalex.org/W1529558080","https://openalex.org/W1545761024","https://openalex.org/W1550698229","https://openalex.org/W1606832378","https://openalex.org/W1646707810","https://openalex.org/W1771410628","https://openalex.org/W1777239053","https://openalex.org/W1815093352","https://openalex.org/W1898511152","https://openalex.org/W1946137962","https://openalex.org/W1968436459","https://openalex.org/W1977655452","https://openalex.org/W1994616650","https://openalex.org/W1995033525","https://openalex.org/W2009303086","https://openalex.org/W2015418199","https://openalex.org/W2015904350","https://openalex.org/W2044287460","https://openalex.org/W2046513829","https://openalex.org/W2047364871","https://openalex.org/W2071983464","https://openalex.org/W2072931156","https://openalex.org/W2075268401","https://openalex.org/W2086161653","https://openalex.org/W2100677568","https://openalex.org/W2110144538","https://openalex.org/W2116680122","https://openalex.org/W2121863487","https://openalex.org/W2128038973","https://openalex.org/W2128659236","https://openalex.org/W2129809168","https://openalex.org/W2131831090","https://openalex.org/W2132849848","https://openalex.org/W2134042548","https://openalex.org/W2139418546","https://openalex.org/W2147750403","https://openalex.org/W2150621701","https://openalex.org/W2151661095","https://openalex.org/W2153290280","https://openalex.org/W2155027007","https://openalex.org/W2165905123","https://openalex.org/W2294586855","https://openalex.org/W2520501711","https://openalex.org/W2561828331","https://openalex.org/W2765393021","https://openalex.org/W2913243980","https://openalex.org/W2962737466","https://openalex.org/W2962755279","https://openalex.org/W2963672698","https://openalex.org/W3041202696","https://openalex.org/W4233696721","https://openalex.org/W4245296547","https://openalex.org/W6630907848","https://openalex.org/W6636255209","https://openalex.org/W6638018090","https://openalex.org/W6638088447","https://openalex.org/W6640697403","https://openalex.org/W6678866754","https://openalex.org/W6679599195","https://openalex.org/W6680307681","https://openalex.org/W6683204974","https://openalex.org/W6684488654","https://openalex.org/W6726059432","https://openalex.org/W6727147046","https://openalex.org/W6730493233","https://openalex.org/W6732811253","https://openalex.org/W6758804334","https://openalex.org/W6761434553","https://openalex.org/W6764419582","https://openalex.org/W6769467134"],"related_works":["https://openalex.org/W3091853547","https://openalex.org/W2798989470","https://openalex.org/W1493119321","https://openalex.org/W3092621452","https://openalex.org/W3103182070","https://openalex.org/W2343385342","https://openalex.org/W3202491425","https://openalex.org/W2145060720","https://openalex.org/W2994143999","https://openalex.org/W1504265534","https://openalex.org/W3147478359","https://openalex.org/W2399915317","https://openalex.org/W2139816856","https://openalex.org/W38986720","https://openalex.org/W2782777630","https://openalex.org/W2964091929","https://openalex.org/W3034848451","https://openalex.org/W2963185456","https://openalex.org/W3158974429","https://openalex.org/W1996627310"],"abstract_inverted_index":{"We":[0,17,40,86],"consider":[1],"policy":[2],"evaluation":[3,84],"in":[4,54],"infinite-horizon":[5],"discounted":[6],"Markov":[7],"decision":[8,29],"problems":[9],"with":[10,26,56,114,117,130,169],"continuous":[11],"compact":[12],"state":[13],"and":[14,133,143],"action":[15],"spaces.":[16],"reformulate":[18],"this":[19,42,88],"task":[20],"as":[21],"a":[22,27,34,45,100,141,170],"compositional":[23],"stochastic":[24,50,57,103],"program":[25],"function-valued":[28],"variable":[30],"that":[31,71,123,144],"belongs":[32,125],"to":[33,81,106,109,126,140,161],"reproducing":[35],"kernel":[36,91],"Hilbert":[37],"space":[38],"(RKHS).":[39],"approach":[41],"problem":[43],"via":[44],"new":[46],"functional":[47],"generalization":[48],"of":[49,66,78,172],"quasi-gradient":[51],"methods":[52],"operating":[53],"tandem":[55],"sparse":[58],"subspace":[59],"projections.":[60],"The":[61],"result":[62],"is":[63,99],"an":[64],"extension":[65],"gradient":[67,92],"temporal":[68,93],"difference":[69,94],"learning":[70],"yields":[72],"nonlinearly":[73],"parameterized":[74],"value":[75,146],"function":[76,147],"estimates":[77,148],"the":[79,82,110,121,127,145,153,173],"solution":[80],"Bellman":[83,111,163],"equation.":[85],"call":[87],"method":[89,104],"parsimonious":[90],"learning.":[95],"Our":[96],"main":[97],"contribution":[98],"memory-efficient":[101],"nonparametric":[102],"guaranteed":[105],"converge":[107],"exactly":[108],"fixed":[112],"point":[113],"probability":[115],"1":[116],"attenuating":[118],"step-sizes":[119,132],"under":[120],"hypothesis":[122],"it":[124],"RKHS.":[128],"Further,":[129],"constant":[131],"compression":[134],"budget,":[135],"we":[136,157],"establish":[137],"mean":[138],"convergence":[139,160],"neighborhood":[142],"have":[149],"finite":[150],"complexity.":[151],"In":[152],"Mountain":[154],"Car":[155],"domain,":[156],"observe":[158],"faster":[159],"lower":[162],"error":[164],"solutions":[165],"than":[166],"existing":[167],"approaches":[168],"fraction":[171],"required":[174],"memory.":[175]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
