{"id":"https://openalex.org/W2106332781","doi":"https://doi.org/10.1109/ijcnn.2007.4370979","title":"Optimality of LSTD and its Relation to MC","display_name":"Optimality of LSTD and its Relation to MC","publication_year":2007,"publication_date":"2007-08-01","ids":{"openalex":"https://openalex.org/W2106332781","doi":"https://doi.org/10.1109/ijcnn.2007.4370979","mag":"2106332781"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2007.4370979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2007.4370979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 International Joint Conference on Neural Networks","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/A5034255459","display_name":"Steffen Gr\u00fcnew\u00e4lder","orcid":"https://orcid.org/0000-0002-4017-2048"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Steffen Grunewalder","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Technology, Berlin, GER. email: gruenew@cs.tu-berlin.de","Univ. of Technol. Berlin, Berlin"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Technology, Berlin, GER. email: gruenew@cs.tu-berlin.de","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"Univ. of Technol. Berlin, Berlin","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053148274","display_name":"Sepp Hochreiter","orcid":"https://orcid.org/0000-0001-7449-2528"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sepp Hochreiter","raw_affiliation_strings":["Department of Information Systems, JKU, Linz, AUS","Department of Information Systems, JKU Linz, AUS. email: gruenew@cs.tu-berlin.de"],"affiliations":[{"raw_affiliation_string":"Department of Information Systems, JKU, Linz, AUS","institution_ids":[]},{"raw_affiliation_string":"Department of Information Systems, JKU Linz, AUS. email: gruenew@cs.tu-berlin.de","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103171859","display_name":"Klaus Obermayer","orcid":"https://orcid.org/0000-0002-5057-6142"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus Obermayer","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Technology, Berlin, GER","Department of Information Systems, JKU Linz, Australia","Department of Electrical Engineering and Computer Science, University of Technology, Berlin, GER. email: gruenew@cs.tu-berlin.de"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Technology, Berlin, GER","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"Department of Information Systems, JKU Linz, Australia","institution_ids":[]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Technology, Berlin, GER. email: gruenew@cs.tu-berlin.de","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034255459"],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":0.9659,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82593654,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"338","last_page":"343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9945999979972839,"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":0.9945999979972839,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9876000285148621,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9817000031471252,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7933992147445679},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.7208764553070068},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.48301586508750916},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.47650471329689026},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.466727614402771},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4660429060459137},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4111771583557129},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3988046944141388},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.22029492259025574}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7933992147445679},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.7208764553070068},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.48301586508750916},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.47650471329689026},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.466727614402771},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4660429060459137},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4111771583557129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3988046944141388},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22029492259025574}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ijcnn.2007.4370979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2007.4370979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 International Joint Conference on Neural Networks","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.lancs.ac.uk:85096","is_oa":false,"landing_page_url":"https://eprints.lancs.ac.uk/id/eprint/85096/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401916","display_name":"Lancaster EPrints (Lancaster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67415387","host_organization_name":"Lancaster University","host_organization_lineage":["https://openalex.org/I67415387"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Contribution in Book/Report/Proceedings"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:1323910","is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/1323910/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:  2007 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-6.  (pp. 338 - 343).  IEEE (2007)     ","raw_type":"Proceedings paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W250076511","https://openalex.org/W1531229281","https://openalex.org/W1583330603","https://openalex.org/W1597303641","https://openalex.org/W1716849269","https://openalex.org/W1965392255","https://openalex.org/W2022261649","https://openalex.org/W2072931156","https://openalex.org/W2100677568","https://openalex.org/W2113913482","https://openalex.org/W2121863487","https://openalex.org/W2122759946","https://openalex.org/W2159951376","https://openalex.org/W2165131254","https://openalex.org/W2312609093","https://openalex.org/W3041202696","https://openalex.org/W4214717370","https://openalex.org/W4246906609","https://openalex.org/W4253978526","https://openalex.org/W4302561155","https://openalex.org/W6634932503","https://openalex.org/W6635767209"],"related_works":["https://openalex.org/W2151689585","https://openalex.org/W2380816257","https://openalex.org/W3087071515","https://openalex.org/W4283726152","https://openalex.org/W4287880334","https://openalex.org/W1525770572","https://openalex.org/W4366700029","https://openalex.org/W1485888979","https://openalex.org/W4285230481","https://openalex.org/W3172507773"],"abstract_inverted_index":{"In":[0],"this":[1],"analytical":[2],"study":[3],"we":[4,61],"compare":[5],"the":[6,9,14,23,41,48,64,76,90],"risk":[7,34],"of":[8,25,43,79,89],"Monte":[10,49,65],"Carlo":[11,50,66],"(MC)":[12],"and":[13,59],"least-squares":[15],"TD":[16],"(LSTD)":[17],"estimator.":[18],"We":[19],"prove":[20],"that":[21,63],"for":[22,35],"case":[24],"acyclic":[26],"Markov":[27,57],"Reward":[28],"Processes":[29],"(MRPs)":[30],"LSTD":[31,71],"has":[32],"minimal":[33],"any":[36],"convex":[37],"loss":[38],"function":[39],"in":[40],"class":[42],"unbiased":[44],"estimators.":[45,91],"When":[46],"comparing":[47],"estimator,":[51],"which":[52],"does":[53],"not":[54],"assume":[55],"a":[56],"structure,":[58],"LSTD,":[60],"find":[62],"estimator":[67],"is":[68],"equivalent":[69],"to":[70],"if":[72],"both":[73],"estimators":[74],"have":[75],"same":[77],"amount":[78],"information.":[80],"Theoretical":[81],"results":[82],"are":[83],"supported":[84],"by":[85],"an":[86],"empirical":[87],"evaluation":[88]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}