{"id":"https://openalex.org/W2734333713","doi":"https://doi.org/10.1109/ijcnn.2017.7966065","title":"Policy gradient methods with Gaussian process modelling acceleration","display_name":"Policy gradient methods with Gaussian process modelling acceleration","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2734333713","doi":"https://doi.org/10.1109/ijcnn.2017.7966065","mag":"2734333713"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2017.7966065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7966065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5101751776","display_name":"Li Dong","orcid":"https://orcid.org/0000-0003-2036-1009"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dong Li","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Automation, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Automation, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Automation, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Automation, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101736381","display_name":"Qichao Zhang","orcid":"https://orcid.org/0000-0002-8278-7083"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qichao Zhang","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Automation, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Automation, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038203605","display_name":"Chaomin Luo","orcid":"https://orcid.org/0000-0002-7578-3631"},"institutions":[{"id":"https://openalex.org/I71792333","display_name":"University of Detroit Mercy","ror":"https://ror.org/0037qsh65","country_code":"US","type":"education","lineage":["https://openalex.org/I71792333"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaomin Luo","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Detroit Mercy, Detroit, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Detroit Mercy, Detroit, USA","institution_ids":["https://openalex.org/I71792333"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101751776"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.7801,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79020829,"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":"1774","last_page":"1779"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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":0.9983000159263611,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9962000250816345,"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":0.9912999868392944,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.7967044115066528},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.6983302235603333},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6153101921081543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6040219068527222},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5397717356681824},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45391398668289185},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4397001266479492},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.38055750727653503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3754483759403229},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23310300707817078},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08497342467308044},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0793469250202179}],"concepts":[{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.7967044115066528},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.6983302235603333},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6153101921081543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6040219068527222},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5397717356681824},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45391398668289185},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4397001266479492},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38055750727653503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3754483759403229},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23310300707817078},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08497342467308044},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0793469250202179},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2017.7966065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7966065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"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/W1840435438","https://openalex.org/W1949804828","https://openalex.org/W2069017697","https://openalex.org/W2119717200","https://openalex.org/W2122021878","https://openalex.org/W2145339207","https://openalex.org/W2153290280","https://openalex.org/W2155027007","https://openalex.org/W2156974606","https://openalex.org/W2160815625","https://openalex.org/W2165150801","https://openalex.org/W2183137222","https://openalex.org/W2194775991","https://openalex.org/W2312229020","https://openalex.org/W2342744201","https://openalex.org/W2524771588","https://openalex.org/W2963864421","https://openalex.org/W4211049957","https://openalex.org/W4214717370","https://openalex.org/W4302570325","https://openalex.org/W6683204974","https://openalex.org/W6684205842"],"related_works":["https://openalex.org/W2565094479","https://openalex.org/W2390829436","https://openalex.org/W1989791859","https://openalex.org/W602859758","https://openalex.org/W2006439817","https://openalex.org/W1971289376","https://openalex.org/W1964286703","https://openalex.org/W2169866437","https://openalex.org/W2953364237","https://openalex.org/W4300623128"],"abstract_inverted_index":{"Policy":[0],"gradient":[1,34],"algorithm":[2,40,91],"is":[3,41,50,60],"often":[4],"used":[5,61,79],"to":[6,43,62,80,92,95],"deal":[7],"with":[8,35],"the":[9,21,73,82,106,113],"continuous":[10],"control":[11],"problems.":[12],"But":[13],"as":[14],"a":[15,32],"model-free":[16],"algorithm,":[17],"it":[18],"suffers":[19],"from":[20],"low":[22],"data":[23],"efficiency":[24],"and":[25,75,84,105],"long":[26],"learning":[27,45,114],"phase.":[28,115],"In":[29],"this":[30],"paper,":[31],"policy":[33],"Gaussian":[36,53,98],"process":[37,54,99],"modelling":[38],"(PGGPM)":[39],"proposed":[42],"accelerate":[44],"process.":[46],"The":[47],"system":[48,103],"model":[49,104],"approximated":[51],"by":[52,68],"in":[55],"an":[56],"incremental":[57],"way,":[58],"which":[59],"explore":[63],"state":[64],"action":[65],"space":[66],"virtually":[67],"generating":[69],"imaginary":[70,76,108],"samples.":[71],"Both":[72],"real":[74],"samples":[77,109],"are":[78],"train":[81],"actor":[83],"critic":[85],"networks.":[86],"Finally,":[87],"we":[88],"apply":[89],"our":[90],"two":[93],"experiments":[94],"verify":[96],"that":[97],"can":[100,110],"accurately":[101],"fit":[102],"supplementary":[107],"speed":[111],"up":[112]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}