{"id":"https://openalex.org/W2159566498","doi":"https://doi.org/10.1007/s10458-008-9056-7","title":"Learning and planning in environments with delayed feedback","display_name":"Learning and planning in environments with delayed feedback","publication_year":2008,"publication_date":"2008-07-03","ids":{"openalex":"https://openalex.org/W2159566498","doi":"https://doi.org/10.1007/s10458-008-9056-7","mag":"2159566498"},"language":"en","primary_location":{"id":"doi:10.1007/s10458-008-9056-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10458-008-9056-7","pdf_url":null,"source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"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":"Autonomous Agents and Multi-Agent Systems","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/A5071800632","display_name":"Thomas J. Walsh","orcid":"https://orcid.org/0000-0002-4142-8711"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Thomas J. Walsh","raw_affiliation_strings":["Department of Computer Science, Rutgers University, 110 Frelinghuysen Rd., Piscataway, NJ, 08854, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, 110 Frelinghuysen Rd., Piscataway, NJ, 08854, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101715103","display_name":"Ali Nouri","orcid":"https://orcid.org/0000-0001-9464-0516"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Nouri","raw_affiliation_strings":["Department of Computer Science, Rutgers University, 110 Frelinghuysen Rd., Piscataway, NJ, 08854, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, 110 Frelinghuysen Rd., Piscataway, NJ, 08854, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056769914","display_name":"Lihong Li","orcid":"https://orcid.org/0000-0003-0205-1349"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lihong Li","raw_affiliation_strings":["Department of Computer Science, Rutgers University, 110 Frelinghuysen Rd., Piscataway, NJ, 08854, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, 110 Frelinghuysen Rd., Piscataway, NJ, 08854, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009722403","display_name":"Michael L. Littman","orcid":"https://orcid.org/0000-0002-5596-1840"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Littman","raw_affiliation_strings":["Department of Computer Science, Rutgers University, 110 Frelinghuysen Rd., Piscataway, NJ, 08854, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, 110 Frelinghuysen Rd., Piscataway, NJ, 08854, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5071800632"],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":1.7598,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.88536329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"18","issue":"1","first_page":"83","last_page":"105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9966999888420105,"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":0.9966999888420105,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9966999888420105,"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/T12288","display_name":"Optimization and Search Problems","score":0.9900000095367432,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7855080366134644},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6557257771492004},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5797171592712402},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.5736231207847595},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4328758716583252},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.42405465245246887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3669911026954651},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.31889599561691284},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16445761919021606},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11039060354232788}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7855080366134644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6557257771492004},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5797171592712402},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.5736231207847595},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4328758716583252},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42405465245246887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3669911026954651},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.31889599561691284},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16445761919021606},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11039060354232788},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10458-008-9056-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10458-008-9056-7","pdf_url":null,"source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"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":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.148.4115","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.148.4115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.rutgers.edu/~lihong/pub/Walsh09Planning.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6200000047683716}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W6242441","https://openalex.org/W107583932","https://openalex.org/W199168817","https://openalex.org/W1497915382","https://openalex.org/W1515851193","https://openalex.org/W1515891729","https://openalex.org/W1550698229","https://openalex.org/W1584530380","https://openalex.org/W1595483645","https://openalex.org/W1597173708","https://openalex.org/W1974730074","https://openalex.org/W1981276685","https://openalex.org/W2008136256","https://openalex.org/W2026076901","https://openalex.org/W2032100464","https://openalex.org/W2039439610","https://openalex.org/W2098432798","https://openalex.org/W2103012681","https://openalex.org/W2113913482","https://openalex.org/W2117864026","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2125074935","https://openalex.org/W2128920470","https://openalex.org/W2129670787","https://openalex.org/W2148213782","https://openalex.org/W2168359464","https://openalex.org/W2334782222","https://openalex.org/W2622604310","https://openalex.org/W4214717370","https://openalex.org/W4233413206","https://openalex.org/W4245296547","https://openalex.org/W4285719527","https://openalex.org/W6604362843","https://openalex.org/W6631000544","https://openalex.org/W6679401659"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W187740018"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}