{"id":"https://openalex.org/W2155938881","doi":"https://doi.org/10.1007/s10626-009-0078-3","title":"On-Line Policy Gradient Estimation with Multi-Step Sampling","display_name":"On-Line Policy Gradient Estimation with Multi-Step Sampling","publication_year":2009,"publication_date":"2009-07-27","ids":{"openalex":"https://openalex.org/W2155938881","doi":"https://doi.org/10.1007/s10626-009-0078-3","mag":"2155938881"},"language":"en","primary_location":{"id":"doi:10.1007/s10626-009-0078-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10626-009-0078-3","pdf_url":null,"source":{"id":"https://openalex.org/S134484881","display_name":"Discrete Event Dynamic Systems","issn_l":"0924-6703","issn":["0924-6703","1573-7594"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discrete Event Dynamic Systems","raw_type":"journal-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/A5100677176","display_name":"Yanjie Li","orcid":"https://orcid.org/0000-0001-6091-0303"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Yan-Jie Li","raw_affiliation_strings":["Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102095806","display_name":"Fang Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Fang Cao","raw_affiliation_strings":["Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100635237","display_name":"Xi\u2010Ren Cao","orcid":"https://orcid.org/0000-0001-5165-8804"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xi-Ren Cao","raw_affiliation_strings":["Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100677176"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.9059,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82063345,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"20","issue":"1","first_page":"3","last_page":"17"},"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.983299970626831,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/sampling","display_name":"Sampling (signal processing)","score":0.6605088114738464},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.6315381526947021},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5485334396362305},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5386092662811279},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5329208374023438},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5069206357002258},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4773992598056793},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.4727388620376587},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.45696064829826355},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.4192092716693878},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31849053502082825},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.21366319060325623},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10993701219558716},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08138588070869446},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.06543460488319397}],"concepts":[{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6605088114738464},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.6315381526947021},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5485334396362305},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5386092662811279},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5329208374023438},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5069206357002258},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4773992598056793},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.4727388620376587},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.45696064829826355},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.4192092716693878},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31849053502082825},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.21366319060325623},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10993701219558716},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08138588070869446},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.06543460488319397},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10626-009-0078-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10626-009-0078-3","pdf_url":null,"source":{"id":"https://openalex.org/S134484881","display_name":"Discrete Event Dynamic Systems","issn_l":"0924-6703","issn":["0924-6703","1573-7594"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discrete Event Dynamic Systems","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-17264","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-17264","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W14520547","https://openalex.org/W1544193923","https://openalex.org/W1814308503","https://openalex.org/W2096899507","https://openalex.org/W2098432798","https://openalex.org/W2108682071","https://openalex.org/W2119567691","https://openalex.org/W2120465407","https://openalex.org/W2144446635","https://openalex.org/W2159871982","https://openalex.org/W2171033527","https://openalex.org/W2334782222","https://openalex.org/W2611866857","https://openalex.org/W3019365222","https://openalex.org/W3026026050","https://openalex.org/W3103182070","https://openalex.org/W3145128584","https://openalex.org/W4253991977","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1660242800","https://openalex.org/W2077211377","https://openalex.org/W3152686072","https://openalex.org/W1006270037","https://openalex.org/W3129238073","https://openalex.org/W2056274461","https://openalex.org/W162527578","https://openalex.org/W2330004501","https://openalex.org/W2017089693","https://openalex.org/W2703295919"],"abstract_inverted_index":null,"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
