{"id":"https://openalex.org/W1553647006","doi":"https://doi.org/10.1007/11564096_25","title":"Towards Finite-Sample Convergence of Direct Reinforcement Learning","display_name":"Towards Finite-Sample Convergence of Direct Reinforcement Learning","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W1553647006","doi":"https://doi.org/10.1007/11564096_25","mag":"1553647006"},"language":"en","primary_location":{"id":"doi:10.1007/11564096_25","is_oa":true,"landing_page_url":"https://doi.org/10.1007/11564096_25","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F11564096_25.pdf","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":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007%2F11564096_25.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081958802","display_name":"Shiau Hong Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shiau Hong Lim","raw_affiliation_strings":["Dept. of Computer Science, University of Illinois, Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043767069","display_name":"Gerald DeJong","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald DeJong","raw_affiliation_strings":["Dept. of Computer Science, University of Illinois, Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081958802"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.2493,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52924945,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"230","last_page":"241"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9925000071525574,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9717000126838684,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/convergence","display_name":"Convergence (economics)","score":0.7479884028434753},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6830136775970459},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6555544137954712},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.45839107036590576},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4116951525211334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.274894118309021},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2504660189151764},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12341484427452087},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.07552677392959595},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07176214456558228}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7479884028434753},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6830136775970459},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6555544137954712},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.45839107036590576},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4116951525211334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.274894118309021},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2504660189151764},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12341484427452087},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.07552677392959595},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07176214456558228},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/11564096_25","is_oa":true,"landing_page_url":"https://doi.org/10.1007/11564096_25","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F11564096_25.pdf","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"}],"best_oa_location":{"id":"doi:10.1007/11564096_25","is_oa":true,"landing_page_url":"https://doi.org/10.1007/11564096_25","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F11564096_25.pdf","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"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1553647006.pdf","grobid_xml":"https://content.openalex.org/works/W1553647006.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1505937442","https://openalex.org/W1515851193","https://openalex.org/W1576452626","https://openalex.org/W1931792391","https://openalex.org/W1981276685","https://openalex.org/W1982948368","https://openalex.org/W2107726111","https://openalex.org/W2118686230","https://openalex.org/W2122701159","https://openalex.org/W2124175081","https://openalex.org/W2489939061","https://openalex.org/W2492794003","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3011120880","https://openalex.org/W3023407077","https://openalex.org/W3139377883","https://openalex.org/W4285719527","https://openalex.org/W4301630257","https://openalex.org/W4307347247"],"related_works":["https://openalex.org/W2923653485","https://openalex.org/W2957776456","https://openalex.org/W4319773215","https://openalex.org/W4224287422","https://openalex.org/W2952472710","https://openalex.org/W4255994452","https://openalex.org/W4206669594","https://openalex.org/W3005560120","https://openalex.org/W3037422413","https://openalex.org/W2959276766"],"abstract_inverted_index":null,"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
