{"id":"https://openalex.org/W4400073208","doi":"https://doi.org/10.1007/s10994-024-06573-4","title":"Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds","display_name":"Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds","publication_year":2024,"publication_date":"2024-06-27","ids":{"openalex":"https://openalex.org/W4400073208","doi":"https://doi.org/10.1007/s10994-024-06573-4"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-024-06573-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-024-06573-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06573-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06573-4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065211579","display_name":"Gabor Paczolay","orcid":"https://orcid.org/0000-0002-4698-1540"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]},{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["HU","IT"],"is_corresponding":true,"raw_author_name":"Gabor Paczolay","raw_affiliation_strings":["Budapest University of Technology and Economics, Budapest, Hungary","Politecnico di Milano, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015303026","display_name":"Matteo Papini","orcid":"https://orcid.org/0000-0002-3807-3171"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Matteo Papini","raw_affiliation_strings":["Politecnico di Milano, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037963323","display_name":"Alberto Maria Metelli","orcid":"https://orcid.org/0000-0002-3424-5212"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Maria Metelli","raw_affiliation_strings":["Politecnico di Milano, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073884445","display_name":"Istv\u00e1n Harmati","orcid":"https://orcid.org/0000-0002-0915-9718"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Istvan Harmati","raw_affiliation_strings":["Budapest University of Technology and Economics, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017130830","display_name":"Marcello Restelli","orcid":"https://orcid.org/0000-0002-6322-1076"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marcello Restelli","raw_affiliation_strings":["Politecnico di Milano, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5065211579"],"corresponding_institution_ids":["https://openalex.org/I29770179","https://openalex.org/I93860229"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07565257,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"113","issue":"9","first_page":"6475","last_page":"6510"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9889000058174133,"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/variance","display_name":"Variance (accounting)","score":0.6958010792732239},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.6444541215896606},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5757634043693542},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5167093276977539},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.4520381689071655},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.41611990332603455},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2917385697364807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25847548246383667},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.19288921356201172},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07196331024169922}],"concepts":[{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6958010792732239},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.6444541215896606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5757634043693542},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5167093276977539},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.4520381689071655},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.41611990332603455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2917385697364807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25847548246383667},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.19288921356201172},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07196331024169922},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10994-024-06573-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-024-06573-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06573-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1269295","is_oa":false,"landing_page_url":"https://hdl.handle.net/11311/1269295","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s10994-024-06573-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-024-06573-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06573-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3786257525","display_name":null,"funder_award_id":"PE00000013","funder_id":"https://openalex.org/F4320331528","funder_display_name":"Ministero dell'Universit\u00e0 e della Ricerca"}],"funders":[{"id":"https://openalex.org/F4320331528","display_name":"Ministero dell'Universit\u00e0 e della Ricerca","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400073208.pdf","grobid_xml":"https://content.openalex.org/works/W4400073208.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1979985652","https://openalex.org/W2006722592","https://openalex.org/W2091565802","https://openalex.org/W2105875671","https://openalex.org/W2107438106","https://openalex.org/W2119567691","https://openalex.org/W2119717200","https://openalex.org/W2120678009","https://openalex.org/W2125612430","https://openalex.org/W2144446635","https://openalex.org/W2148053762","https://openalex.org/W2155027007","https://openalex.org/W2158782408","https://openalex.org/W2304667012","https://openalex.org/W2594182398","https://openalex.org/W2594203335","https://openalex.org/W2767133776","https://openalex.org/W2808489849","https://openalex.org/W2810882972","https://openalex.org/W2944187456","https://openalex.org/W2945752060","https://openalex.org/W2947580152","https://openalex.org/W2954295423","https://openalex.org/W2964312760","https://openalex.org/W2974544365","https://openalex.org/W2993258424","https://openalex.org/W3008654577","https://openalex.org/W3009440920","https://openalex.org/W3022566517","https://openalex.org/W3037541411","https://openalex.org/W3039845099","https://openalex.org/W3080910898","https://openalex.org/W3082245592","https://openalex.org/W3103047293","https://openalex.org/W3132054471","https://openalex.org/W3186110329","https://openalex.org/W3200962355","https://openalex.org/W4210870706","https://openalex.org/W4221158036","https://openalex.org/W4280579036","https://openalex.org/W4319323677","https://openalex.org/W4402672014","https://openalex.org/W6638018090","https://openalex.org/W6676997247","https://openalex.org/W6677916085","https://openalex.org/W6679257226","https://openalex.org/W6683195989","https://openalex.org/W6712159208","https://openalex.org/W6751972096","https://openalex.org/W6762029327","https://openalex.org/W6779452704","https://openalex.org/W6798003472","https://openalex.org/W7001894244"],"related_works":["https://openalex.org/W2964179321","https://openalex.org/W1922851888","https://openalex.org/W1185300216","https://openalex.org/W2607437843","https://openalex.org/W4295700147","https://openalex.org/W2963162727","https://openalex.org/W1563551083","https://openalex.org/W2106714532","https://openalex.org/W4297979791","https://openalex.org/W4221158036"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-09T07:00:12.390032","created_date":"2025-10-10T00:00:00"}
