{"id":"https://openalex.org/W172667874","doi":"https://doi.org/10.1007/978-3-642-33486-3_14","title":"Policy Iteration Based on a Learned Transition Model","display_name":"Policy Iteration Based on a Learned Transition Model","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W172667874","doi":"https://doi.org/10.1007/978-3-642-33486-3_14","mag":"172667874"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-33486-3_14","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-642-33486-3_14","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-642-33486-3_14.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-642-33486-3_14.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010127861","display_name":"Vivek Ramavajjala","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vivek Ramavajjala","raw_affiliation_strings":["Department of Computer Science & Engineering, University of California, San Diego, La Jolla, CA, 92092, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, University of California, San Diego, La Jolla, CA, 92092, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038246567","display_name":"Charles Elkan","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Elkan","raw_affiliation_strings":["Department of Computer Science & Engineering, University of California, San Diego, La Jolla, CA, 92092, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, University of California, San Diego, La Jolla, CA, 92092, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010127861"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.6344,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67982371,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"211","last_page":"226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9591000080108643,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10768","display_name":"Electric Vehicles and Infrastructure","score":0.9521999955177307,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7929478883743286},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7004081606864929},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.52886563539505},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5087175965309143},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5005996227264404},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47683635354042053},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4587988257408142},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.44986438751220703},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4185546338558197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3986490070819855},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3453536033630371},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16957718133926392},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13095837831497192}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7929478883743286},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7004081606864929},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.52886563539505},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5087175965309143},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5005996227264404},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47683635354042053},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4587988257408142},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.44986438751220703},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4185546338558197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3986490070819855},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3453536033630371},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16957718133926392},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13095837831497192},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-642-33486-3_14","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-642-33486-3_14","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-642-33486-3_14.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-642-33486-3_14","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-642-33486-3_14","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-642-33486-3_14.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W172667874.pdf","grobid_xml":"https://content.openalex.org/works/W172667874.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W34092776","https://openalex.org/W192412155","https://openalex.org/W965082120","https://openalex.org/W1499697567","https://openalex.org/W1515851193","https://openalex.org/W1585546346","https://openalex.org/W1854866626","https://openalex.org/W1972645269","https://openalex.org/W1998172110","https://openalex.org/W2026503511","https://openalex.org/W2041684917","https://openalex.org/W2068052921","https://openalex.org/W2108281899","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2123979492","https://openalex.org/W2131831090","https://openalex.org/W2158462832","https://openalex.org/W2161795906","https://openalex.org/W2171890636","https://openalex.org/W2186159582","https://openalex.org/W4214717370","https://openalex.org/W4235282977","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698","https://openalex.org/W1501190258","https://openalex.org/W3021988786","https://openalex.org/W4256087190","https://openalex.org/W3099311996","https://openalex.org/W4240668504","https://openalex.org/W2788366696"],"abstract_inverted_index":null,"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}