{"id":"https://openalex.org/W7169779671","doi":"https://doi.org/10.1016/j.artint.2026.104589","title":"Policy optimization for CMDPs with bandit feedback: Best-of-both-worlds and beyond","display_name":"Policy optimization for CMDPs with bandit feedback: Best-of-both-worlds and beyond","publication_year":2026,"publication_date":"2026-07-20","ids":{"openalex":"https://openalex.org/W7169779671","doi":"https://doi.org/10.1016/j.artint.2026.104589"},"language":"en","primary_location":{"id":"doi:10.1016/j.artint.2026.104589","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.artint.2026.104589","pdf_url":null,"source":{"id":"https://openalex.org/S196139623","display_name":"Artificial Intelligence","issn_l":"0004-3702","issn":["0004-3702","1872-7921"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.artint.2026.104589","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5141194568","display_name":"Francesco Emanuele Stradi","orcid":"https://orcid.org/0009-0008-1200-4187"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francesco Emanuele Stradi","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0008-1200-4187","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098822609","display_name":"Anna Lunghi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anna Lunghi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018390908","display_name":"Matteo Castiglioni","orcid":"https://orcid.org/0000-0002-1070-6766"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matteo Castiglioni","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1070-6766","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039843107","display_name":"Alberto Marchesi","orcid":"https://orcid.org/0000-0002-8284-5757"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alberto Marchesi","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8284-5757","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060367013","display_name":"Nicola Gatti","orcid":"https://orcid.org/0000-0001-7349-3932"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicola Gatti","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7349-3932","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3670,"currency":"USD","value_usd":3670},"apc_paid":{"value":3670,"currency":"USD","value_usd":3670},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.92520852,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"358","issue":null,"first_page":"104589","last_page":"104589"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.8001000285148621,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.8001000285148621,"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":0.045499999076128006,"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/T11182","display_name":"Auction Theory and Applications","score":0.03280000016093254,"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/optimization-problem","display_name":"Optimization problem","score":0.2720000147819519},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.25870001316070557},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.2085999995470047},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.20839999616146088}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5853000283241272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4097000062465668},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3707999885082245},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2387000024318695},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21359999477863312},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2085999995470047},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.20839999616146088},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.20730000734329224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.artint.2026.104589","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.artint.2026.104589","pdf_url":null,"source":{"id":"https://openalex.org/S196139623","display_name":"Artificial Intelligence","issn_l":"0004-3702","issn":["0004-3702","1872-7921"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.artint.2026.104589","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.artint.2026.104589","pdf_url":null,"source":{"id":"https://openalex.org/S196139623","display_name":"Artificial Intelligence","issn_l":"0004-3702","issn":["0004-3702","1872-7921"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324039","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2074680702","https://openalex.org/W4254175217","https://openalex.org/W7133227981"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-24T06:01:01.537669","created_date":"2026-07-21T00:00:00"}