{"id":"https://openalex.org/W2029278774","doi":"https://doi.org/10.1109/acc.2012.6315368","title":"The importance of variance reduction in policy gradient method","display_name":"The importance of variance reduction in policy gradient method","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2029278774","doi":"https://doi.org/10.1109/acc.2012.6315368","mag":"2029278774"},"language":"en","primary_location":{"id":"doi:10.1109/acc.2012.6315368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2012.6315368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 American Control Conference (ACC)","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/A5065237478","display_name":"Tak Kit Lau","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tak Kit Lau","raw_affiliation_strings":["Department of Mechanical and Automation Engineering, Chinese University of Hong Kong, China","Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong,,China"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Automation Engineering, Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong,,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110779740","display_name":"Liu Yunhui","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun-hui Liu","raw_affiliation_strings":["Department of Mechanical and Automation Engineering, Chinese University of Hong Kong, China","Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong,,China"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Automation Engineering, Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong,,China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065237478"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09151493,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"1376","last_page":"1381"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9991000294685364,"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/T12676","display_name":"Machine Learning and ELM","score":0.9688000082969666,"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/tweaking","display_name":"Tweaking","score":0.9490481615066528},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8307517766952515},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.785577118396759},{"id":"https://openalex.org/keywords/variance-reduction","display_name":"Variance reduction","score":0.7421205043792725},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6365254521369934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6140873432159424},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5750579237937927},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5391403436660767},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4525151252746582},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44927653670310974},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.44710710644721985},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.2975693941116333},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23125645518302917},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.08114293217658997},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.07373157143592834}],"concepts":[{"id":"https://openalex.org/C2780200862","wikidata":"https://www.wikidata.org/wiki/Q4453309","display_name":"Tweaking","level":2,"score":0.9490481615066528},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8307517766952515},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.785577118396759},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.7421205043792725},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6365254521369934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6140873432159424},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5750579237937927},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5391403436660767},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4525151252746582},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44927653670310974},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.44710710644721985},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2975693941116333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23125645518302917},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.08114293217658997},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.07373157143592834},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acc.2012.6315368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2012.6315368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W203276351","https://openalex.org/W1601974704","https://openalex.org/W2006036383","https://openalex.org/W2094227853","https://openalex.org/W2099757497","https://openalex.org/W2100677568","https://openalex.org/W2108682071","https://openalex.org/W2127107099","https://openalex.org/W2155027007","https://openalex.org/W2164708536","https://openalex.org/W2292999476","https://openalex.org/W3041202696","https://openalex.org/W6635991215","https://openalex.org/W6676023451","https://openalex.org/W6683204974"],"related_works":["https://openalex.org/W4241780599","https://openalex.org/W2968428037","https://openalex.org/W1981619058","https://openalex.org/W2152101763","https://openalex.org/W4244708442","https://openalex.org/W4323777416","https://openalex.org/W2505446473","https://openalex.org/W2057518680","https://openalex.org/W4394339218","https://openalex.org/W2738037186"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,63],"(RL)":[2],"has":[3],"been":[4],"applied":[5,109],"to":[6,76,110],"a":[7,24,94],"wide":[8],"range":[9],"of":[10,27,45,51,61],"motion":[11],"control":[12],"problems":[13],"in":[14,80],"robotics.":[15],"In":[16,65],"particular,":[17],"policy":[18],"gradient":[19],"method":[20],"(PGM)":[21],"emerges":[22],"as":[23],"powerful":[25],"subset":[26],"RL":[28],"that":[29,70,91],"can":[30,106],"learn":[31],"effectively":[32],"from":[33],"one's":[34],"experience.":[35],"However,":[36],"when":[37],"the":[38,49,59,62,77,81,103],"dynamics":[39],"is":[40,43,73,98],"stochastic":[41],"and":[42,55,87],"short":[44],"samples":[46],"for":[47],"learning,":[48],"performance":[50],"PGM":[52,105],"becomes":[53],"inconsistent":[54],"heavily":[56],"relies":[57],"on":[58,102],"tweaking":[60],"rate.":[64],"this":[66,71],"work,":[67],"we":[68,89],"argue":[69],"degeneration":[72],"mainly":[74],"due":[75],"high":[78],"variance":[79,95],"gradient.":[82],"Through":[83],"theoretical":[84],"justifications,":[85],"simulations":[86],"experiments,":[88],"verify":[90],"by":[92],"applying":[93],"suppression,":[96],"which":[97],"called":[99],"local":[100],"baseline,":[101],"gradient,":[104],"then":[107],"be":[108],"some":[111],"previously":[112],"untouchable":[113],"problems.":[114]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}