{"id":"https://openalex.org/W2134540127","doi":"https://doi.org/10.1007/978-3-642-15880-3_44","title":"Gaussian Processes for Sample Efficient Reinforcement Learning with RMAX-Like Exploration","display_name":"Gaussian Processes for Sample Efficient Reinforcement Learning with RMAX-Like Exploration","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2134540127","doi":"https://doi.org/10.1007/978-3-642-15880-3_44","mag":"2134540127"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-15880-3_44","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-15880-3_44","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050771291","display_name":"Tobias Jung","orcid":"https://orcid.org/0000-0002-9159-8444"},"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":true,"raw_author_name":"Tobias Jung","raw_affiliation_strings":["Department of Computer Science, University of Texas at Austin,","Dept. of Computer Science, University of Texas at Austin#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin,","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Dept. of Computer Science, University of Texas at Austin#TAB#","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","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,","Dept. of Computer Science, University of Texas at Austin#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin,","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Dept. of Computer Science, University of Texas at Austin#TAB#","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050771291"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.6993,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.8603814,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"601","last_page":"616"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9973000288009644,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9973000288009644,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9884999990463257,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9832000136375427,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6678836345672607},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6608723402023315},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6054990887641907},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5725325345993042},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5672126412391663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5655717253684998},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5320134162902832},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.522786557674408},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4490257203578949},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42952239513397217},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.42214563488960266},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3582995533943176},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20166486501693726}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6678836345672607},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6608723402023315},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6054990887641907},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5725325345993042},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5672126412391663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5655717253684998},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5320134162902832},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.522786557674408},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4490257203578949},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42952239513397217},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.42214563488960266},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3582995533943176},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20166486501693726},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-642-15880-3_44","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-15880-3_44","pdf_url":null,"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":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/W1505937442","https://openalex.org/W1515851193","https://openalex.org/W1552830313","https://openalex.org/W1746819321","https://openalex.org/W2018547649","https://openalex.org/W2058212189","https://openalex.org/W2084202551","https://openalex.org/W2104245950","https://openalex.org/W2106907982","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2130819374","https://openalex.org/W2132849848","https://openalex.org/W2133120480","https://openalex.org/W2145756561","https://openalex.org/W2150923691","https://openalex.org/W2154032554","https://openalex.org/W2963705262","https://openalex.org/W4211049957","https://openalex.org/W4214717370","https://openalex.org/W4242606736","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4296474751","https://openalex.org/W4360764167","https://openalex.org/W3147214434","https://openalex.org/W2251221343","https://openalex.org/W4295309597","https://openalex.org/W4386337009","https://openalex.org/W3081580854","https://openalex.org/W4287683259","https://openalex.org/W4384929195","https://openalex.org/W4384932390"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}