{"id":"https://openalex.org/W1539216098","doi":"https://doi.org/10.1016/b978-1-55860-377-6.50052-9","title":"Learning policies for partially observable environments: Scaling up","display_name":"Learning policies for partially observable environments: Scaling up","publication_year":1995,"publication_date":"1995-01-01","ids":{"openalex":"https://openalex.org/W1539216098","doi":"https://doi.org/10.1016/b978-1-55860-377-6.50052-9","mag":"1539216098"},"language":"en","primary_location":{"id":"doi:10.1016/b978-1-55860-377-6.50052-9","is_oa":false,"landing_page_url":"https://doi.org/10.1016/b978-1-55860-377-6.50052-9","pdf_url":null,"source":{"id":"https://openalex.org/S4306463230","display_name":"Elsevier eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning Proceedings 1995","raw_type":"book-chapter"},"type":"book-chapter","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/A5009722403","display_name":"Michael L. Littman","orcid":"https://orcid.org/0000-0002-5596-1840"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael L. Littman","raw_affiliation_strings":["Department of Computer Science, Brown University, Providence, RI 02912-1910"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Brown University, Providence, RI 02912-1910","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023048350","display_name":"Anthony R. Cassandra","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Anthony R. Cassandra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012862284","display_name":"Leslie Pack Kaelbling","orcid":null},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Leslie Pack Kaelbling","raw_affiliation_strings":["Department of Computer Science, Brown University, Providence, RI 02912-1910"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Brown University, Providence, RI 02912-1910","institution_ids":["https://openalex.org/I27804330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5009722403","https://openalex.org/A5012862284","https://openalex.org/A5023048350"],"corresponding_institution_ids":["https://openalex.org/I27804330"],"apc_list":null,"apc_paid":null,"fwci":23.0902,"has_fulltext":false,"cited_by_count":665,"citation_normalized_percentile":{"value":0.99634236,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"362","last_page":"370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976999759674072,"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":0.9976999759674072,"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":0.9891999959945679,"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":0.9886999726295471,"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/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.9650288224220276},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.6725253462791443},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6404278874397278},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5355306267738342},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5253426432609558},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.46751052141189575},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.44732943177223206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4237228035926819},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33927541971206665},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.33436357975006104},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.31670039892196655},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.24973055720329285},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.18733221292495728},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14839166402816772}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.9650288224220276},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.6725253462791443},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6404278874397278},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5355306267738342},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5253426432609558},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.46751052141189575},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.44732943177223206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4237228035926819},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33927541971206665},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.33436357975006104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31670039892196655},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.24973055720329285},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.18733221292495728},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14839166402816772},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1016/b978-1-55860-377-6.50052-9","is_oa":false,"landing_page_url":"https://doi.org/10.1016/b978-1-55860-377-6.50052-9","pdf_url":null,"source":{"id":"https://openalex.org/S4306463230","display_name":"Elsevier eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning Proceedings 1995","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.41.1514","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.41.1514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.brown.edu/research/ai/pomdp/papers/./cs-95-11.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.41.5994","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.41.5994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.brown.edu/research/ai/pomdp/papers/./ml95.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.52.6374","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.52.6374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ubc.ca/spider/cclaus/papers/kaelb_scale.ps","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":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W95627046","https://openalex.org/W131709709","https://openalex.org/W969698184","https://openalex.org/W1538075516","https://openalex.org/W1539216098","https://openalex.org/W1545148916","https://openalex.org/W1591195137","https://openalex.org/W1650504995","https://openalex.org/W1657674574","https://openalex.org/W1831612509","https://openalex.org/W1966195676","https://openalex.org/W2011418219","https://openalex.org/W2032100464","https://openalex.org/W2034725503","https://openalex.org/W2044375425","https://openalex.org/W2054726834","https://openalex.org/W2065087844","https://openalex.org/W2099873296","https://openalex.org/W2113335124","https://openalex.org/W2122410182","https://openalex.org/W2165131254","https://openalex.org/W4231226883","https://openalex.org/W4233840023","https://openalex.org/W4298856952","https://openalex.org/W6625382770","https://openalex.org/W6636774213","https://openalex.org/W6664103266","https://openalex.org/W6775686901","https://openalex.org/W6812527618"],"related_works":["https://openalex.org/W2999848267","https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W3174905945","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W4323315247"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":29},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":42},{"year":2020,"cited_by_count":25},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":26},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":22},{"year":2015,"cited_by_count":29},{"year":2014,"cited_by_count":24},{"year":2013,"cited_by_count":28},{"year":2012,"cited_by_count":31}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}