{"id":"https://openalex.org/W4224925640","doi":"https://doi.org/10.1109/tnnls.2022.3165941","title":"Partial Consistency for Stabilizing Undiscounted Reinforcement Learning","display_name":"Partial Consistency for Stabilizing Undiscounted Reinforcement Learning","publication_year":2022,"publication_date":"2022-04-25","ids":{"openalex":"https://openalex.org/W4224925640","doi":"https://doi.org/10.1109/tnnls.2022.3165941","pmid":"https://pubmed.ncbi.nlm.nih.gov/35468065"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3165941","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3165941","pdf_url":"https://ieeexplore.ieee.org/ielx7/5962385/6104215/09762369.pdf","source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/5962385/6104215/09762369.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013839754","display_name":"Haichuan Gao","orcid":"https://orcid.org/0000-0002-5161-5326"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haichuan Gao","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","Department of Automation, Tsinghua University, Beijing 100084, China"],"raw_orcid":"https://orcid.org/0000-0002-5161-5326","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107229776","display_name":"Zhile Yang","orcid":"https://orcid.org/0000-0002-7908-9524"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhile Yang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","Department of Automation, Tsinghua University, Beijing 100084, China"],"raw_orcid":"https://orcid.org/0000-0002-7908-9524","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101667380","display_name":"Tian Tan","orcid":"https://orcid.org/0000-0001-9173-2984"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian Tan","raw_affiliation_strings":["Department of Civil and Environmental Engineering, Stanford University, Stanford, CA, USA","Department of Civil and Environmental Engineering, Stanford University, Stanford, CA 94305 USA"],"raw_orcid":"https://orcid.org/0000-0001-9173-2984","affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Stanford University, Stanford, CA 94305 USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026023372","display_name":"Tianren Zhang","orcid":"https://orcid.org/0000-0001-9687-5263"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianren Zhang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","Department of Automation, Tsinghua University, Beijing 100084, China"],"raw_orcid":"https://orcid.org/0000-0001-9687-5263","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044602016","display_name":"Jinsheng Ren","orcid":"https://orcid.org/0000-0002-5013-1880"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinsheng Ren","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","Department of Automation, Tsinghua University, Beijing 100084, China"],"raw_orcid":"https://orcid.org/0000-0002-5013-1880","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056581926","display_name":"Pengfei Sun","orcid":"https://orcid.org/0000-0003-4169-8874"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Sun","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","Department of Automation, Tsinghua University, Beijing 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048321911","display_name":"Shangqi Guo","orcid":"https://orcid.org/0000-0003-3181-6881"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangqi Guo","raw_affiliation_strings":["Department of Automation and the Department of Precision Instrument, Tsinghua University, Beijing, China","Department of Automation and the Department of Precision Instrument, Tsinghua University, Beijing 100086, China"],"raw_orcid":"https://orcid.org/0000-0003-3181-6881","affiliations":[{"raw_affiliation_string":"Department of Automation and the Department of Precision Instrument, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation and the Department of Precision Instrument, Tsinghua University, Beijing 100086, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100352754","display_name":"Feng Chen","orcid":"https://orcid.org/0000-0003-4813-2494"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Chen","raw_affiliation_strings":["Department of Automation, Center for Brain-Inspired Computing Research, Tsinghua University, Beijing, China","Center for Brain-Inspired Computing Research, Department of Automation, Tsinghua University, Beijing 100190, China, and also with the LSBDPA Beijing Key Laboratory, Beijing 100084, China"],"raw_orcid":"https://orcid.org/0000-0003-4813-2494","affiliations":[{"raw_affiliation_string":"Department of Automation, Center for Brain-Inspired Computing Research, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Brain-Inspired Computing Research, Department of Automation, Tsinghua University, Beijing 100190, China, and also with the LSBDPA Beijing Key Laboratory, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58906531,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"34","issue":"12","first_page":"10359","last_page":"10373"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9861000180244446,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9772999882698059,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7696505188941956},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6742494702339172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6373010873794556},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5849360823631287},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5094802975654602},{"id":"https://openalex.org/keywords/instability","display_name":"Instability","score":0.50291508436203},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.46527713537216187},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4631589651107788},{"id":"https://openalex.org/keywords/transient","display_name":"Transient (computer programming)","score":0.4525418281555176},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4468056261539459},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4275619685649872},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.41630226373672485},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.41515955328941345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3803837299346924},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35952842235565186},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28617218136787415},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24110475182533264},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.16726472973823547},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12387093901634216},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0916864275932312}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7696505188941956},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6742494702339172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6373010873794556},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5849360823631287},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5094802975654602},{"id":"https://openalex.org/C207821765","wikidata":"https://www.wikidata.org/wiki/Q405372","display_name":"Instability","level":2,"score":0.50291508436203},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.46527713537216187},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4631589651107788},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.4525418281555176},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4468056261539459},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4275619685649872},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.41630226373672485},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.41515955328941345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3803837299346924},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35952842235565186},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28617218136787415},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24110475182533264},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.16726472973823547},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12387093901634216},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0916864275932312},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C57879066","wikidata":"https://www.wikidata.org/wiki/Q41217","display_name":"Mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2022.3165941","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3165941","pdf_url":"https://ieeexplore.ieee.org/ielx7/5962385/6104215/09762369.pdf","source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:35468065","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35468065","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":{"id":"doi:10.1109/tnnls.2022.3165941","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3165941","pdf_url":"https://ieeexplore.ieee.org/ielx7/5962385/6104215/09762369.pdf","source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2641599095","display_name":null,"funder_award_id":"2021ZD0200300","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3395539601","display_name":null,"funder_award_id":"2021ZD0200300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5220867262","display_name":null,"funder_award_id":"62176133","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7861851748","display_name":"\u901a\u7528\u7c7b\u8111\u8ba1\u7b97\u67b6\u6784\u6a21\u578b\u4e0e\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61836004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4224925640.pdf","grobid_xml":"https://content.openalex.org/works/W4224925640.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W1549353711","https://openalex.org/W2056354534","https://openalex.org/W2081287319","https://openalex.org/W2082511574","https://openalex.org/W2113913482","https://openalex.org/W2135574445","https://openalex.org/W2145339207","https://openalex.org/W2161950876","https://openalex.org/W2182573229","https://openalex.org/W2405532007","https://openalex.org/W2522489477","https://openalex.org/W2574020264","https://openalex.org/W2596367596","https://openalex.org/W2604842041","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2767050701","https://openalex.org/W2947241716","https://openalex.org/W2962847657","https://openalex.org/W2962957005","https://openalex.org/W2963019567","https://openalex.org/W2963523627","https://openalex.org/W2963713397","https://openalex.org/W2963871073","https://openalex.org/W2969761570","https://openalex.org/W2989186172","https://openalex.org/W2998461398","https://openalex.org/W3036453832","https://openalex.org/W3088521775","https://openalex.org/W3101442004","https://openalex.org/W3131533760","https://openalex.org/W3134619122","https://openalex.org/W3164385739","https://openalex.org/W3168202624","https://openalex.org/W3174733757","https://openalex.org/W3187587412","https://openalex.org/W4214717370","https://openalex.org/W4295113716","https://openalex.org/W6627932998","https://openalex.org/W6629282427","https://openalex.org/W6635516443","https://openalex.org/W6639926649","https://openalex.org/W6677179944","https://openalex.org/W6678114464","https://openalex.org/W6712794944","https://openalex.org/W6735579001","https://openalex.org/W6735641298","https://openalex.org/W6741002519","https://openalex.org/W6746684068","https://openalex.org/W6748929038","https://openalex.org/W6751869817","https://openalex.org/W6771217966","https://openalex.org/W6779587693","https://openalex.org/W6779605008","https://openalex.org/W6779715229","https://openalex.org/W6780815668"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2022300913","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W1570780624","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W14400985","https://openalex.org/W2024136090","https://openalex.org/W2322569264"],"abstract_inverted_index":{"Undiscounted":[0],"return":[1,19],"is":[2,43,95,104,137],"an":[3,17],"important":[4],"setup":[5],"in":[6,74,107],"reinforcement":[7],"learning":[8],"(RL)":[9],"and":[10,84,126,175],"characterizes":[11],"many":[12],"real-world":[13],"problems.":[14],"However,":[15,69],"optimizing":[16],"undiscounted":[18],"often":[20],"causes":[21,25],"training":[22,85,166],"instability.":[23],"The":[24,51,111,130],"of":[26,48,102,168],"this":[27,39,41],"instability":[28,57],"problem":[29,42],"have":[30],"not":[31],"been":[32],"analyzed":[33,44],"in-depth":[34],"by":[35,65,139],"existing":[36],"studies.":[37],"In":[38],"article,":[40],"from":[45,59],"the":[46,56,75,108,115,122,127,134,146,161,165],"perspective":[47],"value":[49,117,125,136],"estimation.":[50],"analysis":[52],"result":[53],"indicates":[54],"that":[55,62,99,133,145,160],"originates":[58],"transient":[60,151],"traps":[61,152],"are":[63],"caused":[64],"inconsistently":[66],"selected":[67,105,141],"actions.":[68,142],"selecting":[70],"one":[71],"consistent":[72],"action":[73],"same":[76,109],"state":[77],"limits":[78],"exploration.":[79],"For":[80],"balancing":[81],"exploration":[82],"effectiveness":[83],"stability,":[86],"a":[87,100],"novel":[88],"sampling":[89,93],"method":[90,113,148,162],"called":[91],"last-visit":[92,123],"(LVS)":[94],"proposed":[96],"to":[97],"ensure":[98],"part":[101],"actions":[103],"consistently":[106,140],"state.":[110],"LVS":[112,147],"decomposes":[114],"state-action":[116],"into":[118],"two":[119],"parts,":[120],"i.e.,":[121],"(LV)":[124],"revisit":[128],"value.":[129],"decomposition":[131],"ensures":[132],"LV":[135],"determined":[138],"We":[143],"prove":[144],"can":[149,163],"eliminate":[150],"while":[153],"preserving":[154],"optimality.":[155],"Also,":[156],"we":[157],"empirically":[158],"show":[159],"stabilize":[164],"processes":[167],"five":[169],"typical":[170],"tasks,":[171],"including":[172],"vision-based":[173],"navigation":[174],"manipulation":[176],"tasks.":[177]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}