{"id":"https://openalex.org/W3009446012","doi":"https://doi.org/10.5555/2627435.2638563","title":"Policy evaluation with temporal differences","display_name":"Policy evaluation with temporal differences","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W3009446012","doi":"https://doi.org/10.5555/2627435.2638563","mag":"3009446012"},"language":"en","primary_location":{"id":"mag:3009446012","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.5555/2627435.2638563","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research","raw_type":null},"type":"article","indexed_in":[],"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/A5062599169","display_name":"DannChristoph","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"DannChristoph","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012297447","display_name":"NeumannGerhard","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"NeumannGerhard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001148393","display_name":"PetersJan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"PetersJan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.31721799,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.24639999866485596,"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":0.24639999866485596,"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/T11043","display_name":"Merger and Competition Analysis","score":0.2289000004529953,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11675","display_name":"Open Source Software Innovations","score":0.21889999508857727,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.6144710183143616},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5790071487426758},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5777347683906555},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5310820937156677},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5121326446533203},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4965386986732483},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.49039506912231445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3927841782569885},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32621335983276367},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24908480048179626},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.23262956738471985},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.1136462390422821}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6144710183143616},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5790071487426758},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5777347683906555},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5310820937156677},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5121326446533203},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4965386986732483},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.49039506912231445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3927841782569885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32621335983276367},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24908480048179626},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.23262956738471985},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.1136462390422821},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3009446012","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.5555/2627435.2638563","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Journal of Machine Learning Research","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3170225685","https://openalex.org/W3173679269","https://openalex.org/W3004798888","https://openalex.org/W3037134744","https://openalex.org/W1977969926","https://openalex.org/W2591313450","https://openalex.org/W2649888023","https://openalex.org/W620943832","https://openalex.org/W2496962556","https://openalex.org/W3033351689","https://openalex.org/W2079862821","https://openalex.org/W604670222","https://openalex.org/W1574701935","https://openalex.org/W1585327923","https://openalex.org/W2054232829","https://openalex.org/W2999407277","https://openalex.org/W2507492379","https://openalex.org/W2196972133","https://openalex.org/W2361419931"],"abstract_inverted_index":{"Policy":[0],"evaluation":[1],"is":[2],"an":[3],"essential":[4],"step":[5],"in":[6,29],"most":[7],"reinforcement":[8],"learning":[9],"approaches.":[10],"It":[11],"yields":[12],"a":[13,22,30],"value":[14],"function,":[15],"the":[16],"quality":[17],"assessment":[18],"of":[19],"states":[20],"for":[21],"given":[23],"policy,":[24],"which":[25],"can":[26],"be":[27],"used":[28],"policy":[31],"impr...":[32]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-10-10T17:16:08.811792","created_date":"2025-10-10T00:00:00"}