{"id":"https://openalex.org/W2889558211","doi":"https://doi.org/10.1587/transinf.2017edp7363","title":"Incremental Estimation of Natural Policy Gradient with Relative Importance Weighting","display_name":"Incremental Estimation of Natural Policy Gradient with Relative Importance Weighting","publication_year":2018,"publication_date":"2018-08-31","ids":{"openalex":"https://openalex.org/W2889558211","doi":"https://doi.org/10.1587/transinf.2017edp7363","mag":"2889558211"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2017edp7363","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2017edp7363","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E101.D/9/E101.D_2017EDP7363/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E101.D/9/E101.D_2017EDP7363/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069735496","display_name":"Ryo Iwaki","orcid":null},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo IWAKI","raw_affiliation_strings":["Osaka University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102889260","display_name":"H. Yokoyama","orcid":"https://orcid.org/0000-0003-3142-3914"},"institutions":[{"id":"https://openalex.org/I149481174","display_name":"Tamagawa University","ror":"https://ror.org/05f8a4p63","country_code":"JP","type":"education","lineage":["https://openalex.org/I149481174"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroki YOKOYAMA","raw_affiliation_strings":["Tamagawa University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tamagawa University","institution_ids":["https://openalex.org/I149481174"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044985800","display_name":"Minoru Asada","orcid":"https://orcid.org/0000-0001-9506-6333"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Minoru ASADA","raw_affiliation_strings":["Osaka University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09797053,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"E101.D","issue":"9","first_page":"2346","last_page":"2355"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","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/T12072","display_name":"Machine Learning and Algorithms","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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9969000220298767,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9968000054359436,"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/weighting","display_name":"Weighting","score":0.8494319915771484},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7634329795837402},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.7412705421447754},{"id":"https://openalex.org/keywords/overshoot","display_name":"Overshoot (microwave communication)","score":0.5636327266693115},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5430341362953186},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.44487398862838745},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4317779242992401},{"id":"https://openalex.org/keywords/a-weighting","display_name":"A-weighting","score":0.42892026901245117},{"id":"https://openalex.org/keywords/two-step","display_name":"Two step","score":0.42548540234565735},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33147722482681274},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2423703670501709},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.20181211829185486}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.8494319915771484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7634329795837402},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.7412705421447754},{"id":"https://openalex.org/C2780323453","wikidata":"https://www.wikidata.org/wiki/Q7113957","display_name":"Overshoot (microwave communication)","level":2,"score":0.5636327266693115},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5430341362953186},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44487398862838745},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4317779242992401},{"id":"https://openalex.org/C70136482","wikidata":"https://www.wikidata.org/wiki/Q13583781","display_name":"A-weighting","level":3,"score":0.42892026901245117},{"id":"https://openalex.org/C3019136120","wikidata":"https://www.wikidata.org/wiki/Q2462428","display_name":"Two step","level":2,"score":0.42548540234565735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33147722482681274},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2423703670501709},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.20181211829185486},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2017edp7363","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2017edp7363","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E101.D/9/E101.D_2017EDP7363/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2017edp7363","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2017edp7363","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E101.D/9/E101.D_2017EDP7363/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4155471703","display_name":null,"funder_award_id":"JPMJCR17A4","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6718509927","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7604265505","display_name":null,"funder_award_id":"JPMJCR17A4","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G8571218779","display_name":"Constructive Developmental Science Based on Understanding the Process from Neuro-Dynamics to Social Interaction","funder_award_id":"24000012","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2889558211.pdf","grobid_xml":"https://content.openalex.org/works/W2889558211.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1500331901","https://openalex.org/W1522301498","https://openalex.org/W1594783240","https://openalex.org/W1967459934","https://openalex.org/W1970789124","https://openalex.org/W1971942712","https://openalex.org/W2024390895","https://openalex.org/W2094387729","https://openalex.org/W2100563667","https://openalex.org/W2106261932","https://openalex.org/W2112964839","https://openalex.org/W2113501460","https://openalex.org/W2145339207","https://openalex.org/W2146502635","https://openalex.org/W2153874061","https://openalex.org/W2155027007","https://openalex.org/W2166886563","https://openalex.org/W2172968643","https://openalex.org/W2257979135","https://openalex.org/W2282463321","https://openalex.org/W2563217198","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2092002118","https://openalex.org/W1880952682","https://openalex.org/W1963516324","https://openalex.org/W2014269659","https://openalex.org/W1971836599","https://openalex.org/W2019002543","https://openalex.org/W2619302272","https://openalex.org/W2180954594","https://openalex.org/W2075728349","https://openalex.org/W2033210010"],"abstract_inverted_index":{"The":[0,46],"step":[1,27,38,49,84,102,119],"size":[2,28,39,50,103,120],"is":[3,62,115],"a":[4],"parameter":[5,55],"of":[6,99,111],"fundamental":[7],"importance":[8],"in":[9,29],"learning":[10,67],"algorithms,":[11],"particularly":[12],"for":[13,25,82,91,122],"the":[14,26,42,59,66,83,92,97,100,105,109,116],"natural":[15],"policy":[16],"gradient":[17],"(NPG)":[18],"methods.":[19],"We":[20,74,95],"derive":[21],"an":[22,30,36,53],"upper":[23,44,78],"bound":[24],"incremental":[31,93],"NPG":[32,123],"estimation,":[33],"and":[34,79],"propose":[35],"adaptive":[37,48,118],"to":[40,70],"implement":[41],"derived":[43],"bound.":[45],"proposed":[47,101],"guarantees":[51],"that":[52],"updated":[54],"does":[56],"not":[57,89],"overshoot":[58],"target,":[60],"which":[61],"achieved":[63],"by":[64],"weighting":[65],"samples":[68],"according":[69],"their":[71],"relative":[72],"importances.":[73],"also":[75],"provide":[76],"tight":[77],"lower":[80],"bounds":[81],"size,":[85],"though":[86],"they":[87],"are":[88],"suitable":[90],"learning.":[94],"confirm":[96],"usefulness":[98],"using":[104],"classical":[106],"benchmarks.":[107],"To":[108],"best":[110],"our":[112],"knowledge,":[113],"this":[114],"first":[117],"method":[121],"estimation.":[124]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
