{"id":"https://openalex.org/W2017541761","doi":"https://doi.org/10.1109/ijcnn.2012.6252509","title":"Reinforcement learning with guided policy search using Gaussian processes","display_name":"Reinforcement learning with guided policy search using Gaussian processes","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2017541761","doi":"https://doi.org/10.1109/ijcnn.2012.6252509","mag":"2017541761"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2012.6252509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2012.6252509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2012 International Joint Conference on Neural Networks (IJCNN)","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/A5023731260","display_name":"Hunor Jakab","orcid":null},"institutions":[{"id":"https://openalex.org/I3125347698","display_name":"Babe\u0219-Bolyai University","ror":"https://ror.org/02rmd1t30","country_code":"RO","type":"education","lineage":["https://openalex.org/I3125347698"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Hunor S. Jakab","raw_affiliation_strings":["Department of Computer Science, Babe\u015f-Bolyai University, Cluj-Napoca, Romania","Department of Computer Science, Babe\u015f-Bolyai University, RO-400084 Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Babe\u015f-Bolyai University, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I3125347698"]},{"raw_affiliation_string":"Department of Computer Science, Babe\u015f-Bolyai University, RO-400084 Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I3125347698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048206013","display_name":"Lehel Csat\u00f3","orcid":"https://orcid.org/0000-0003-1052-1849"},"institutions":[{"id":"https://openalex.org/I3125347698","display_name":"Babe\u0219-Bolyai University","ror":"https://ror.org/02rmd1t30","country_code":"RO","type":"education","lineage":["https://openalex.org/I3125347698"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Lehel Csato","raw_affiliation_strings":["Department of Computer Science, Babe\u015f-Bolyai University, Cluj-Napoca, Romania","Department of Computer Science, Babe\u015f-Bolyai University, RO-400084 Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Babe\u015f-Bolyai University, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I3125347698"]},{"raw_affiliation_string":"Department of Computer Science, Babe\u015f-Bolyai University, RO-400084 Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I3125347698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5023731260"],"corresponding_institution_ids":["https://openalex.org/I3125347698"],"apc_list":null,"apc_paid":null,"fwci":0.4281,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70981414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9961000084877014,"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":0.9944000244140625,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7461642622947693},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7019389867782593},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6983308792114258},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.6324065327644348},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5572373867034912},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.539585530757904},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5307310223579407},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.528447151184082},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5156513452529907},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.494538277387619},{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.48491960763931274},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4696231186389923},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.46457064151763916},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4212421178817749},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32689371705055237},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2136303186416626}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7461642622947693},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7019389867782593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6983308792114258},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.6324065327644348},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5572373867034912},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.539585530757904},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5307310223579407},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.528447151184082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5156513452529907},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.494538277387619},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.48491960763931274},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4696231186389923},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.46457064151763916},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4212421178817749},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32689371705055237},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2136303186416626},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2012.6252509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2012.6252509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2012 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1483589","https://openalex.org/W15382557","https://openalex.org/W568924265","https://openalex.org/W621546036","https://openalex.org/W1516801383","https://openalex.org/W1646707810","https://openalex.org/W1746819321","https://openalex.org/W2072931156","https://openalex.org/W2100785108","https://openalex.org/W2110304639","https://openalex.org/W2112002204","https://openalex.org/W2119567691","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2125612430","https://openalex.org/W2129564505","https://openalex.org/W2130105540","https://openalex.org/W2130801532","https://openalex.org/W2139053308","https://openalex.org/W2140135625","https://openalex.org/W2151416233","https://openalex.org/W2154032554","https://openalex.org/W2155027007","https://openalex.org/W2312609093","https://openalex.org/W2334782222","https://openalex.org/W2478027467","https://openalex.org/W2954040150","https://openalex.org/W4211049957","https://openalex.org/W4214717370","https://openalex.org/W4241680091","https://openalex.org/W6600051106","https://openalex.org/W6638674303","https://openalex.org/W6675278435","https://openalex.org/W6680657880","https://openalex.org/W6683204974"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"Gradient":[0],"based":[1],"policy":[2],"search":[3],"algorithms":[4],"benefit":[5],"largely":[6],"from":[7],"the":[8,25,28,32,49,52,60,77,95,100,107,127],"availability":[9],"of":[10,27,34,62,76,82,99,129],"a":[11,42,121],"properly":[12],"estimated":[13,53],"state":[14],"or":[15],"state-action":[16,89],"value":[17,38,54],"function":[18,39,55],"which":[19],"can":[20,58],"be":[21],"used":[22],"to":[23,105,110,125],"reduce":[24],"variance":[26],"gradient":[29],"estimates.":[30],"Additionally":[31],"use":[33],"Gaussian":[35,101],"processes":[36,102],"for":[37,72,85],"approximation":[40],"provides":[41],"fully":[43,96],"probabilistic":[44,97],"model":[45],"where":[46],"-":[47,56],"using":[48],"uncertainty":[50],"in":[51,79],"we":[57,68],"assess":[59],"amount":[61],"exploration":[63,78,108],"required.":[64],"In":[65],"this":[66],"article":[67],"present":[69,118],"two":[70],"modalities":[71],"adjusting":[73],"different":[74],"characteristics":[75],"on-line":[80],"learning":[81],"control":[83,123],"policies":[84],"problems":[86],"with":[87],"continuous":[88],"spaces.":[90],"The":[91],"proposed":[92],"methods":[93],"exploit":[94],"nature":[98],"and":[103],"aims":[104],"constrain":[106],"only":[109],"relevant":[111],"subspaces,":[112],"thereby":[113],"speeding":[114],"up":[115],"convergence.":[116],"We":[117],"experiments":[119],"on":[120],"simulated":[122],"task":[124],"demonstrate":[126],"validity":[128],"our":[130],"algorithms.":[131]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}