{"id":"https://openalex.org/W1716849269","doi":"https://doi.org/10.1023/a:1007495401240","title":"Analytical Mean Squared Error Curves for Temporal Difference Learning","display_name":"Analytical Mean Squared Error Curves for Temporal Difference Learning","publication_year":1998,"publication_date":"1998-07-01","ids":{"openalex":"https://openalex.org/W1716849269","doi":"https://doi.org/10.1023/a:1007495401240","mag":"1716849269"},"language":"en","primary_location":{"id":"doi:10.1023/a:1007495401240","is_oa":true,"landing_page_url":"https://doi.org/10.1023/a:1007495401240","pdf_url":"https://link.springer.com/content/pdf/10.1023/A:1007495401240.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1023/A:1007495401240.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065366930","display_name":"Satinder Singh","orcid":"https://orcid.org/0000-0002-2736-7641"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Satinder Singh","raw_affiliation_strings":["Department of Computer Science, University of Colorado, Boulder, CO, 80309-0430","Department of Computer Science, University of Colorado,  Boulder, CO 80309-0430. E-mail: baveja@cs.colorado.edu"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Colorado, Boulder, CO, 80309-0430","institution_ids":["https://openalex.org/I188538660"]},{"raw_affiliation_string":"Department of Computer Science, University of Colorado,  Boulder, CO 80309-0430. E-mail: baveja@cs.colorado.edu","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075063030","display_name":"Peter Dayan","orcid":"https://orcid.org/0000-0003-3476-1839"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Dayan","raw_affiliation_strings":["Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA, 02139","Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA 02139. E-mail: dayan@ai.mit.edu#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA, 02139","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA 02139. E-mail: dayan@ai.mit.edu#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065366930"],"corresponding_institution_ids":["https://openalex.org/I188538660"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":2.747,"has_fulltext":true,"cited_by_count":46,"citation_normalized_percentile":{"value":0.90789834,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"32","issue":"1","first_page":"5","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9937999844551086,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9919000267982483,"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/estimator","display_name":"Estimator","score":0.7426422834396362},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5737119913101196},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.5728578567504883},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.49190330505371094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48581671714782715},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.46889132261276245},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46251431107521057},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.4447823762893677},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4334101974964142},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.426650732755661},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4107426702976227},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3822776973247528},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3685987591743469},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.14818304777145386}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7426422834396362},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5737119913101196},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5728578567504883},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.49190330505371094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48581671714782715},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.46889132261276245},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46251431107521057},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.4447823762893677},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4334101974964142},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.426650732755661},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4107426702976227},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3822776973247528},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3685987591743469},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.14818304777145386},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1023/a:1007495401240","is_oa":true,"landing_page_url":"https://doi.org/10.1023/a:1007495401240","pdf_url":"https://link.springer.com/content/pdf/10.1023/A:1007495401240.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:pure.mpg.de:item_3022419","is_oa":true,"landing_page_url":"https://hdl.handle.net/21.11116/0000-0002-D625-3","pdf_url":"http://hdl.handle.net/21.11116/0000-0002-D625-3","source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.mpg.de:item_3024131","is_oa":true,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0002-E320-9","pdf_url":"http://hdl.handle.net/21.11116/0000-0002-E320-9","source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Advances in Neural Information Processing Systems 9","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:85067","is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/85067/","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: Mozer, MC and Jordan, MI and Petsche, T, (eds.) ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 9.  (pp. 1054 - 1060).  M I T PRESS (1997)     ","raw_type":"Proceedings paper"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:99302","is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/99302/","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":"   MACH LEARN , 32  (1)   5 - 40.   (1998)      ","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1023/a:1007495401240","is_oa":true,"landing_page_url":"https://doi.org/10.1023/a:1007495401240","pdf_url":"https://link.springer.com/content/pdf/10.1023/A:1007495401240.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8133388860","display_name":"Exploiting Structure in Reinforcement Learning Problems","funder_award_id":"9711753","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/F4320332538","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1716849269.pdf","grobid_xml":"https://content.openalex.org/works/W1716849269.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1488002936","https://openalex.org/W1826343992","https://openalex.org/W1965227651","https://openalex.org/W2005937003","https://openalex.org/W2010343671","https://openalex.org/W2038390905","https://openalex.org/W2068778050","https://openalex.org/W2091565802","https://openalex.org/W2100677568","https://openalex.org/W2113913482","https://openalex.org/W2126217565","https://openalex.org/W2147750403","https://openalex.org/W2158091072","https://openalex.org/W2165131254","https://openalex.org/W2199011767","https://openalex.org/W2895674046","https://openalex.org/W3009870883","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W4213058208","https://openalex.org/W4233061323","https://openalex.org/W4233696721","https://openalex.org/W4240813273","https://openalex.org/W4253803546","https://openalex.org/W4253978526","https://openalex.org/W6780394890","https://openalex.org/W7045474554","https://openalex.org/W7075666287"],"related_works":["https://openalex.org/W2131958170","https://openalex.org/W2061122711","https://openalex.org/W2273754158","https://openalex.org/W4247954915","https://openalex.org/W4293088233","https://openalex.org/W2336747664","https://openalex.org/W2357130048","https://openalex.org/W4206605161","https://openalex.org/W2102148524","https://openalex.org/W2221502901"],"abstract_inverted_index":null,"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2016-06-24T00:00:00"}