{"id":"https://openalex.org/W3188986767","doi":"https://doi.org/10.24963/ijcai.2021/341","title":"Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment","display_name":"Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3188986767","doi":"https://doi.org/10.24963/ijcai.2021/341","mag":"3188986767"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/341","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/341","pdf_url":"https://www.ijcai.org/proceedings/2021/0341.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0341.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102669078","display_name":"Jia\u2010Ming Guo","orcid":"https://orcid.org/0000-0003-3200-5255"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"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/I4401726770","display_name":"Cambricon (China)","ror":"https://ror.org/00r2rga43","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726770"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Guo","raw_affiliation_strings":["Cambricon Technologies","SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China","University of Chinese Academy of Sciences, China","Cambricon Technologies; SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China; University of Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambricon Technologies","institution_ids":["https://openalex.org/I4401726770"]},{"raw_affiliation_string":"SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Cambricon Technologies; SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China; University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101573366","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0001-8691-8549"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4401726770","display_name":"Cambricon (China)","ror":"https://ror.org/00r2rga43","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726770"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["Cambricon Technologies","SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambricon Technologies","institution_ids":["https://openalex.org/I4401726770"]},{"raw_affiliation_string":"SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009782388","display_name":"Xishan Zhang","orcid":"https://orcid.org/0000-0002-8574-6199"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4401726770","display_name":"Cambricon (China)","ror":"https://ror.org/00r2rga43","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726770"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xishan Zhang","raw_affiliation_strings":["Cambricon Technologies","SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambricon Technologies","institution_ids":["https://openalex.org/I4401726770"]},{"raw_affiliation_string":"SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069888696","display_name":"Shaohui Peng","orcid":"https://orcid.org/0000-0001-6838-6817"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"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/I4401726770","display_name":"Cambricon (China)","ror":"https://ror.org/00r2rga43","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726770"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohui Peng","raw_affiliation_strings":["Cambricon Technologies","SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China","University of Chinese Academy of Sciences, China","Cambricon Technologies; SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China; University of Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambricon Technologies","institution_ids":["https://openalex.org/I4401726770"]},{"raw_affiliation_string":"SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Cambricon Technologies; SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China; University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062480688","display_name":"Yi Qi","orcid":"https://orcid.org/0000-0002-0959-3450"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4401726770","display_name":"Cambricon (China)","ror":"https://ror.org/00r2rga43","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726770"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Yi","raw_affiliation_strings":["Cambricon Technologies","SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China","University of Science and Technology of China","SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China; University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambricon Technologies","institution_ids":["https://openalex.org/I4401726770"]},{"raw_affiliation_string":"SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China; University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056949827","display_name":"Zidong Du","orcid":"https://orcid.org/0000-0002-7603-4210"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4401726770","display_name":"Cambricon (China)","ror":"https://ror.org/00r2rga43","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726770"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zidong Du","raw_affiliation_strings":["Cambricon Technologies","SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambricon Technologies","institution_ids":["https://openalex.org/I4401726770"]},{"raw_affiliation_string":"SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101964036","display_name":"Xing Hu","orcid":"https://orcid.org/0000-0002-9979-0561"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Hu","raw_affiliation_strings":["SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103063161","display_name":"Qi Guo","orcid":"https://orcid.org/0000-0003-2530-5874"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Guo","raw_affiliation_strings":["SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036492388","display_name":"Yunji Chen","orcid":"https://orcid.org/0000-0003-3925-5185"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunji Chen","raw_affiliation_strings":["CAS Center for Excellence in Brain Science and Intelligence Technology, CEBSIT","SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China","University of Chinese Academy of Sciences, China","CAS Center for Excellence in Brain Science and Intelligence Technology, CEBSIT; SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China; University of Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Center for Excellence in Brain Science and Intelligence Technology, CEBSIT","institution_ids":["https://openalex.org/I4210097554"]},{"raw_affiliation_string":"SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"CAS Center for Excellence in Brain Science and Intelligence Technology, CEBSIT; SKL of Computer Architecture, Institute of Computing Technology, CAS, Beijing, China; University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210097554","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2931,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51834982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2476","last_page":"2482"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9950000047683716,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9902999997138977,"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/hindsight-bias","display_name":"Hindsight bias","score":0.9217438697814941},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.7976335287094116},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.7390650510787964},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.653910756111145},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.633926510810852},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5847739577293396},{"id":"https://openalex.org/keywords/variance-reduction","display_name":"Variance reduction","score":0.5716103315353394},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5200433731079102},{"id":"https://openalex.org/keywords/variance-function","display_name":"Variance function","score":0.46435263752937317},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35153627395629883},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25909674167633057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.240202397108078},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14633840322494507},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.07272538542747498}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.9217438697814941},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.7976335287094116},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.7390650510787964},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.653910756111145},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.633926510810852},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5847739577293396},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.5716103315353394},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5200433731079102},{"id":"https://openalex.org/C120488996","wikidata":"https://www.wikidata.org/wiki/Q17016064","display_name":"Variance function","level":3,"score":0.46435263752937317},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35153627395629883},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25909674167633057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.240202397108078},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14633840322494507},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.07272538542747498},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","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/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/341","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/341","pdf_url":"https://www.ijcai.org/proceedings/2021/0341.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/341","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/341","pdf_url":"https://www.ijcai.org/proceedings/2021/0341.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.49000000953674316,"display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G1183981214","display_name":null,"funder_award_id":"61906179","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1304758712","display_name":null,"funder_award_id":"62002338","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1958237895","display_name":null,"funder_award_id":"JQ18013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2351125877","display_name":null,"funder_award_id":"61732007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3027545885","display_name":null,"funder_award_id":"61925208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5349471034","display_name":null,"funder_award_id":"Z191100001119093","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"},{"id":"https://openalex.org/G571593048","display_name":null,"funder_award_id":"U20A20227","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6322973505","display_name":null,"funder_award_id":"61732002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6511211688","display_name":null,"funder_award_id":"2018AAA0103300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6839492696","display_name":null,"funder_award_id":"U19B2019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3188986767.pdf","grobid_xml":"https://content.openalex.org/works/W3188986767.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1686946872","https://openalex.org/W1771410628","https://openalex.org/W2130801532","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2155027007","https://openalex.org/W2158782408","https://openalex.org/W2257979135","https://openalex.org/W2554984891","https://openalex.org/W2736601468","https://openalex.org/W2786303200","https://openalex.org/W2859870583","https://openalex.org/W2963226019","https://openalex.org/W2964043796","https://openalex.org/W3003384866","https://openalex.org/W3036928441","https://openalex.org/W4214717370","https://openalex.org/W4230563027","https://openalex.org/W4287660295","https://openalex.org/W4288289109"],"related_works":["https://openalex.org/W3197854638","https://openalex.org/W3140454661","https://openalex.org/W4245029315","https://openalex.org/W2139970489","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698","https://openalex.org/W3184322736","https://openalex.org/W3188986767"],"abstract_inverted_index":{"Policy":[0],"gradient":[1,15,83,95],"methods":[2],"are":[3],"appealing":[4],"in":[5,38,125],"deep":[6],"reinforcement":[7],"learning":[8],"but":[9],"suffer":[10],"from":[11,74],"high":[12],"variance":[13,80],"of":[14,31,81,106,112],"estimate.":[16],"To":[17],"reduce":[18,78],"the":[19,21,29,32,43,51,60,72,75,79,82,104,107,120,137,142,149,152,156],"variance,":[20,150],"state":[22,33,45,61,139],"value":[23,34,62,68,123,140,145],"function":[24,35,63,124,146],"is":[25],"applied":[26],"commonly.":[27],"However,":[28],"effect":[30],"becomes":[36],"limited":[37],"stochastic":[39,86,126],"dynamic":[40,87,127],"environments,":[41,128],"where":[42],"unexpected":[44],"dynamics":[46],"and":[47,132,154],"rewards":[48],"will":[49],"increase":[50],"variance.":[52],"In":[53,115],"this":[54],"paper,":[55],"we":[56,97,118],"propose":[57,98],"to":[58,77,90,109],"replace":[59],"with":[64,136],"a":[65],"novel":[66],"hindsight":[67,122,144],"function,":[69,141],"which":[70,102],"leverages":[71],"information":[73],"future":[76,108],"estimate":[84],"for":[85],"environments.":[88,134],"Particularly,":[89],"obtain":[91],"an":[92,99],"ideally":[93],"unbiased":[94],"estimate,":[96],"information-theoretic":[100],"approach,":[101],"optimizes":[103],"embeddings":[105],"be":[110],"independent":[111],"previous":[113],"actions.":[114],"our":[116],"experiments,":[117],"apply":[119],"proposed":[121,143],"including":[129],"discrete-action":[130],"environments":[131],"continuous-action":[133],"Compared":[135],"standard":[138],"consistently":[147],"reduces":[148],"stabilizes":[151],"training,":[153],"improves":[155],"eventual":[157],"policy.":[158]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
