{"id":"https://openalex.org/W3107926684","doi":"https://doi.org/10.1007/978-3-662-63519-3_5","title":"Convergence Proof for Actor-Critic Methods Applied to PPO and RUDDER","display_name":"Convergence Proof for Actor-Critic Methods Applied to PPO and RUDDER","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3107926684","doi":"https://doi.org/10.1007/978-3-662-63519-3_5","mag":"3107926684"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-662-63519-3_5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-662-63519-3_5","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2012.01399","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037001244","display_name":"Markus Holzleitner","orcid":"https://orcid.org/0000-0002-7167-9802"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Markus Holzleitner","raw_affiliation_strings":["ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria","JOHANNES KEPLER UNIVERSITY LINZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"JOHANNES KEPLER UNIVERSITY LINZ","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103843547","display_name":"Lukas Gruber","orcid":null},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Lukas Gruber","raw_affiliation_strings":["ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria","JOHANNES KEPLER UNIVERSITY LINZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"JOHANNES KEPLER UNIVERSITY LINZ","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039286688","display_name":"Jose A. Arjona-Medina","orcid":"https://orcid.org/0000-0002-5033-4725"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]},{"id":"https://openalex.org/I4210121368","display_name":"Machine Science","ror":"https://ror.org/02hrr9v50","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210121368"]}],"countries":["AT","US"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Arjona-Medina","raw_affiliation_strings":["ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria","Institute for Machine Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"Institute for Machine Learning","institution_ids":["https://openalex.org/I4210121368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107411550","display_name":"J. Brandstetter","orcid":"https://orcid.org/0000-0003-3881-976X"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Johannes Brandstetter","raw_affiliation_strings":["ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria","JOHANNES KEPLER UNIVERSITY LINZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"JOHANNES KEPLER UNIVERSITY LINZ","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053148274","display_name":"Sepp Hochreiter","orcid":"https://orcid.org/0000-0001-7449-2528"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]},{"id":"https://openalex.org/I161878677","display_name":"Austrian Research Institute for Artificial Intelligence","ror":"https://ror.org/04j47vk14","country_code":"AT","type":"facility","lineage":["https://openalex.org/I161878677","https://openalex.org/I4210107880"]},{"id":"https://openalex.org/I4210157875","display_name":"Institute of Advanced Research in Artificial Intelligence","ror":"https://ror.org/04m8gxe14","country_code":"AT","type":"facility","lineage":["https://openalex.org/I4210157875"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Sepp Hochreiter","raw_affiliation_strings":["ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria","Institute of Advanced Research in Artificial Intelligence (IARAI), Vienna, Austria","JOHANNES KEPLER UNIVERSITY LINZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"Institute of Advanced Research in Artificial Intelligence (IARAI), Vienna, Austria","institution_ids":["https://openalex.org/I161878677","https://openalex.org/I4210157875"]},{"raw_affiliation_string":"JOHANNES KEPLER UNIVERSITY LINZ","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00851544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"105","last_page":"130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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":0.996399998664856,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/rudder","display_name":"Rudder","score":0.8033977150917053},{"id":"https://openalex.org/keywords/mathematical-proof","display_name":"Mathematical proof","score":0.7108639478683472},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6808210015296936},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.622410237789154},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.620100736618042},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5736384987831116},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5142207145690918},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5046547651290894},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4523228406906128},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.4229559004306793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31079837679862976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26082149147987366},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.06797415018081665}],"concepts":[{"id":"https://openalex.org/C183776436","wikidata":"https://www.wikidata.org/wiki/Q209760","display_name":"Rudder","level":2,"score":0.8033977150917053},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.7108639478683472},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6808210015296936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.622410237789154},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.620100736618042},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5736384987831116},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5142207145690918},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5046547651290894},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4523228406906128},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4229559004306793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31079837679862976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26082149147987366},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.06797415018081665},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/978-3-662-63519-3_5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-662-63519-3_5","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2012.01399","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.01399","pdf_url":"https://arxiv.org/pdf/2012.01399","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3107926684","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2012.01399.pdf","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2012.01399","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2012.01399","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2012.01399","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.01399","pdf_url":"https://arxiv.org/pdf/2012.01399","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W58921469","https://openalex.org/W1499021337","https://openalex.org/W1576452626","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W1899249567","https://openalex.org/W1994616650","https://openalex.org/W2009303086","https://openalex.org/W2049631384","https://openalex.org/W2071983464","https://openalex.org/W2082261506","https://openalex.org/W2098670910","https://openalex.org/W2121863487","https://openalex.org/W2134042548","https://openalex.org/W2145339207","https://openalex.org/W2147750403","https://openalex.org/W2150339816","https://openalex.org/W2155027007","https://openalex.org/W2158091072","https://openalex.org/W2235056388","https://openalex.org/W2341905372","https://openalex.org/W2493209382","https://openalex.org/W2900832763","https://openalex.org/W2907626093","https://openalex.org/W2907669392","https://openalex.org/W2911319680","https://openalex.org/W2947996939","https://openalex.org/W2963446085","https://openalex.org/W2963940330","https://openalex.org/W2963981733","https://openalex.org/W2964232029","https://openalex.org/W2970128053","https://openalex.org/W2970161765","https://openalex.org/W2970705602","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W3089895152","https://openalex.org/W3102076842","https://openalex.org/W3117137507","https://openalex.org/W4243772471","https://openalex.org/W6607687417","https://openalex.org/W6611608239","https://openalex.org/W6725704494","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W2970161765","https://openalex.org/W2958746411","https://openalex.org/W2788366696","https://openalex.org/W2971587637","https://openalex.org/W3165594265","https://openalex.org/W2995081787","https://openalex.org/W2105675791","https://openalex.org/W2560131027","https://openalex.org/W3206440539","https://openalex.org/W2153874061","https://openalex.org/W2963744705","https://openalex.org/W3212744543","https://openalex.org/W2964986650","https://openalex.org/W2293432107","https://openalex.org/W2784825028","https://openalex.org/W2962677091","https://openalex.org/W2465818302","https://openalex.org/W2468145343","https://openalex.org/W2963364412","https://openalex.org/W2980404711"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}
