{"id":"https://openalex.org/W7137880300","doi":"https://doi.org/10.1016/j.neucom.2026.133343","title":"HAVEN: Hierarchical diffusion and value-based trajectory selection for offline safe reinforcement learning","display_name":"HAVEN: Hierarchical diffusion and value-based trajectory selection for offline safe reinforcement learning","publication_year":2026,"publication_date":"2026-03-17","ids":{"openalex":"https://openalex.org/W7137880300","doi":"https://doi.org/10.1016/j.neucom.2026.133343"},"language":"en","primary_location":{"id":"doi:10.1016/j.neucom.2026.133343","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133343","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"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":"Neurocomputing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090876344","display_name":"Erlie Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Erlie Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103783071","display_name":"He Diao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He Diao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129680531","display_name":"Xianglin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianglin Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054919195","display_name":"JingKui Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingkui Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129691260","display_name":"Xiaofeng Chai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaofeng Chai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129718932","display_name":"Qiang Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiang Qi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129746753","display_name":"Ping Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ping Zhang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5090876344"],"corresponding_institution_ids":[],"apc_list":{"value":2470,"currency":"USD","value_usd":2470},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.89577401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"681","issue":null,"first_page":"133343","last_page":"133343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8507000207901001,"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":0.8507000207901001,"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":0.017799999564886093,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.014600000344216824,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7228999733924866},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6485000252723694},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5867999792098999},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.3452000021934509},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.29170000553131104},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.2831999957561493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.756600022315979},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7228999733924866},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6485000252723694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5964999794960022},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5867999792098999},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4503999948501587},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26109999418258667},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2572999894618988},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.neucom.2026.133343","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133343","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"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":"Neurocomputing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W3045503639","https://openalex.org/W3092395313","https://openalex.org/W4281550413","https://openalex.org/W4375855901","https://openalex.org/W4380519997","https://openalex.org/W4385938565","https://openalex.org/W4392979624","https://openalex.org/W4401972299","https://openalex.org/W4405145750","https://openalex.org/W4408309418","https://openalex.org/W4408933567","https://openalex.org/W4411122121","https://openalex.org/W7133190736"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-21T06:30:42.041108","created_date":"2026-03-18T00:00:00"}