{"id":"https://openalex.org/W7127082682","doi":"https://doi.org/10.1016/j.neunet.2026.108667","title":"Improving policy exploitation in online reinforcement learning with instant retrospect action","display_name":"Improving policy exploitation in online reinforcement learning with instant retrospect action","publication_year":2026,"publication_date":"2026-02-02","ids":{"openalex":"https://openalex.org/W7127082682","doi":"https://doi.org/10.1016/j.neunet.2026.108667","pmid":"https://pubmed.ncbi.nlm.nih.gov/41666489"},"language":"en","primary_location":{"id":"doi:10.1016/j.neunet.2026.108667","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neunet.2026.108667","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.19720","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124068504","display_name":"Gong Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gong Gao","raw_affiliation_strings":["School of Computer Science, Tongji University, China. Electronic address: 2310925@tongji.edu.cn"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Tongji University, China. Electronic address: 2310925@tongji.edu.cn","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016584164","display_name":"Weidong Zhao","orcid":"https://orcid.org/0000-0003-4144-7303"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weidong Zhao","raw_affiliation_strings":["School of Computer Science, Tongji University, China. Electronic address: zwd_tj@tongji.edu.cn"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Tongji University, China. Electronic address: zwd_tj@tongji.edu.cn","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125094151","display_name":"Xianhui Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianhui Liu","raw_affiliation_strings":["School of Computer Science, Tongji University, China. Electronic address: xianhui_l@163.com"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Tongji University, China. Electronic address: xianhui_l@163.com","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047695235","display_name":"Ning Jia","orcid":"https://orcid.org/0000-0001-8758-5846"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Jia","raw_affiliation_strings":["School of Computer Science, Tongji University, China. Electronic address: jianing7072@tongji.edu.cn"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Tongji University, China. Electronic address: jianing7072@tongji.edu.cn","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016584164"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":{"value":3350,"currency":"USD","value_usd":3350},"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37746449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"199","issue":null,"first_page":"108667","last_page":"108667"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9193000197410583,"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":0.9193000197410583,"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":0.010499999858438969,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.007899999618530273,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.791100025177002},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5616999864578247},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5299999713897705},{"id":"https://openalex.org/keywords/backtracking","display_name":"Backtracking","score":0.48989999294281006},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4505000114440918},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4498000144958496},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.43650001287460327}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.791100025177002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7547000050544739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.616100013256073},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5616999864578247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5504000186920166},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5299999713897705},{"id":"https://openalex.org/C156884757","wikidata":"https://www.wikidata.org/wiki/Q798554","display_name":"Backtracking","level":2,"score":0.48989999294281006},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C2779432360","wikidata":"https://www.wikidata.org/wiki/Q16963779","display_name":"Instant","level":2,"score":0.4323999881744385},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4309999942779541},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C96640997","wikidata":"https://www.wikidata.org/wiki/Q5163004","display_name":"Conservatism","level":3,"score":0.27300000190734863}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.neunet.2026.108667","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neunet.2026.108667","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},{"id":"pmid:41666489","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41666489","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":"Neural networks : the official journal of the International Neural Network Society","raw_type":null},{"id":"pmh:oai:arXiv.org:2601.19720","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.19720","pdf_url":"https://arxiv.org/pdf/2601.19720","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":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.19720","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.19720","pdf_url":"https://arxiv.org/pdf/2601.19720","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":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.730010449886322}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7127082682.pdf","grobid_xml":"https://content.openalex.org/works/W7127082682.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W4372197859","https://openalex.org/W4394872716","https://openalex.org/W4396705030","https://openalex.org/W4401326497"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-02-12T06:13:03.167441","created_date":"2026-02-02T00:00:00"}