{"id":"https://openalex.org/W2899328950","doi":"https://doi.org/10.1109/tnnls.2018.2871361","title":"Stable and Efficient Policy Evaluation","display_name":"Stable and Efficient Policy Evaluation","publication_year":2018,"publication_date":"2018-10-30","ids":{"openalex":"https://openalex.org/W2899328950","doi":"https://doi.org/10.1109/tnnls.2018.2871361","mag":"2899328950","pmid":"https://pubmed.ncbi.nlm.nih.gov/30387743"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2018.2871361","pdf_url":null,"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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.03978","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025744129","display_name":"Daoming Lyu","orcid":"https://orcid.org/0000-0003-2625-9865"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daoming Lyu","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Auburn University, Auburn, AL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University, Auburn, AL, USA","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030361565","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0003-2519-6196"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Auburn University, Auburn, AL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University, Auburn, AL, USA","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110482875","display_name":"Matthieu Geist","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145544","display_name":"Laboratoire Interdisciplinaire des Environnements Continentaux","ror":"https://ror.org/05je79696","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210107625","https://openalex.org/I4210145544","https://openalex.org/I4210148025","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Matthieu Geist","raw_affiliation_strings":["Laboratoire Interdisciplinaire des Environnements Continentaux, Centre national de la recherche scientifique, Universit\u00e9 de Lorraine, Metz, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire Interdisciplinaire des Environnements Continentaux, Centre national de la recherche scientifique, Universit\u00e9 de Lorraine, Metz, France","institution_ids":["https://openalex.org/I4210145544","https://openalex.org/I90183372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047724274","display_name":"Wen Dong","orcid":"https://orcid.org/0000-0001-8923-2227"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Dong","raw_affiliation_strings":["Department of Computer Science and Engineering, The State University of New York at Buffalo, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The State University of New York at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110660235","display_name":"Sa\u00e2d Biaz","orcid":null},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saad Biaz","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Auburn University, Auburn, AL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University, Auburn, AL, USA","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341321","display_name":"Qi Wang","orcid":"https://orcid.org/0000-0002-7028-4956"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Wang","raw_affiliation_strings":["School of Computer Science and the Center for OPTical IMagery Analysis and Learning, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and the Center for OPTical IMagery Analysis and Learning, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institution_assertions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.518,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":7,"citation_normalized_percentile":{"value":0.792813,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":82,"max":83},"biblio":{"volume":"30","issue":"6","first_page":"1831","last_page":"1840"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9999,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9999,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986,"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/T12676","display_name":"Machine Learning and ELM","score":0.973,"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/policy-learning","display_name":"Policy learning","score":0.43732288}],"concepts":[{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6931929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.68736297},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.66757655},{"id":"https://openalex.org/C160697094","wikidata":"https://www.wikidata.org/wiki/Q1233197","display_name":"Oblique case","level":2,"score":0.5200581},{"id":"https://openalex.org/C123587114","wikidata":"https://www.wikidata.org/wiki/Q2101508","display_name":"Policy analysis","level":2,"score":0.4753506},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.45919976},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45204076},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.43732288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37188506},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3564961},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33950484},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2001963},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.11427379},{"id":"https://openalex.org/C3116431","wikidata":"https://www.wikidata.org/wiki/Q31728","display_name":"Public administration","level":1,"score":0.0741559},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2018.2871361","pdf_url":null,"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":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2006.03978","pdf_url":"https://arxiv.org/pdf/2006.03978","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30387743","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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2006.03978","pdf_url":"https://arxiv.org/pdf/2006.03978","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.53,"display_name":"Peace, justice, and strong institutions"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":22,"referenced_works":["https://openalex.org/W1506342804","https://openalex.org/W1514587017","https://openalex.org/W1547925194","https://openalex.org/W1646707810","https://openalex.org/W1941556277","https://openalex.org/W2048687352","https://openalex.org/W2075268401","https://openalex.org/W2101533993","https://openalex.org/W2106261932","https://openalex.org/W2121703796","https://openalex.org/W2132351269","https://openalex.org/W2139418546","https://openalex.org/W2154761920","https://openalex.org/W2292896113","https://openalex.org/W2395162158","https://openalex.org/W2727279496","https://openalex.org/W2772589676","https://openalex.org/W2800877957","https://openalex.org/W2951143668","https://openalex.org/W2953189830","https://openalex.org/W2963674921","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W4205144164","https://openalex.org/W2962772812","https://openalex.org/W2734376513","https://openalex.org/W2615919102","https://openalex.org/W2320608497","https://openalex.org/W2186686745","https://openalex.org/W2134999447","https://openalex.org/W2070726643","https://openalex.org/W2067516463","https://openalex.org/W2001916836"],"abstract_inverted_index":{"Policy":[0],"evaluation":[1],"algorithms":[2,71,84],"are":[3,21,72,76,86],"essential":[4],"to":[5,9,12,32,48],"reinforcement":[6],"learning":[7],"due":[8],"their":[10],"ability":[11],"predict":[13],"the":[14,53,62,65,95,107,110],"performance":[15],"of":[16,109],"a":[17],"policy.":[18],"However,":[19],"there":[20],"two":[22],"long-standing":[23],"issues":[24],"lying":[25],"in":[26,52],"this":[27],"prediction":[28],"problem":[29],"that":[30,85],"need":[31],"be":[33],"tackled:":[34],"off-policy":[35,59,73,88],"stability":[36],"and":[37,68,90],"on-policy":[38,54,78,91],"efficiency.":[39],"The":[40,99],"conventional":[41],"temporal":[42],"difference":[43],"(TD)":[44],"algorithm":[45],"is":[46,57],"known":[47],"perform":[49],"very":[50],"well":[51],"setting,":[55],"yet":[56],"not":[58,77],"stable.":[60],"On":[61],"other":[63],"hand,":[64],"gradient":[66],"TD":[67,70],"emphatic":[69],"stable,":[74],"but":[75],"efficient.":[79],"This":[80],"paper":[81],"introduces":[82],"novel":[83],"both":[87],"stable":[89],"efficient":[92],"by":[93],"using":[94],"oblique":[96],"projection":[97],"method.":[98],"empirical":[100],"experimental":[101],"results":[102],"on":[103],"various":[104],"domains":[105],"validate":[106],"effectiveness":[108],"proposed":[111],"approach.":[112]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2899328950","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2024-12-10T07:03:36.081330","created_date":"2018-11-09"}