{"id":"https://openalex.org/W4385517529","doi":"https://doi.org/10.1007/978-3-031-39144-6_9","title":"Model-Based Reinforcement Learning with\u00a0State Abstraction: A Survey","display_name":"Model-Based Reinforcement Learning with\u00a0State Abstraction: A Survey","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385517529","doi":"https://doi.org/10.1007/978-3-031-39144-6_9"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-39144-6_9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-39144-6_9","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"Communications in Computer and Information Science","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/A5068066221","display_name":"Rolf A. N. Starre","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Rolf A. N. Starre","raw_affiliation_strings":["Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086060106","display_name":"Marco Loog","orcid":"https://orcid.org/0000-0002-1298-8461"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marco Loog","raw_affiliation_strings":["Radbout University, Nijmegen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Radbout University, Nijmegen, The Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009493909","display_name":"Frans A. Oliehoek","orcid":"https://orcid.org/0000-0003-4372-5055"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Frans A. Oliehoek","raw_affiliation_strings":["Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068066221"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":1.9839,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.87672845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"133","last_page":"148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9860000014305115,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8779791593551636},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7646472454071045},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.7397726774215698},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.683080792427063},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.6293895840644836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6271077394485474},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48561611771583557},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4199264645576477},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.4162874221801758},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4109940528869629},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08108446002006531},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08018207550048828},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.06307387351989746}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8779791593551636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646472454071045},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.7397726774215698},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.683080792427063},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6293895840644836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6271077394485474},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48561611771583557},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4199264645576477},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.4162874221801758},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4109940528869629},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08108446002006531},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08018207550048828},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.06307387351989746},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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":2,"locations":[{"id":"doi:10.1007/978-3-031-39144-6_9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-39144-6_9","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"Communications in Computer and Information Science","raw_type":"book-chapter"},{"id":"pmh:oai:tudelft.nl:uuid:1475bd63-9f2b-4bd9-989f-3e7a160c287a","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:1475bd63-9f2b-4bd9-989f-3e7a160c287a","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1073366937","display_name":"Influence-based Decision-making in Uncertain Environments","funder_award_id":"758824","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W50090763","https://openalex.org/W1164749991","https://openalex.org/W1896074376","https://openalex.org/W1968653071","https://openalex.org/W1988217924","https://openalex.org/W1988526405","https://openalex.org/W2018547649","https://openalex.org/W2046495522","https://openalex.org/W2058735307","https://openalex.org/W2071815241","https://openalex.org/W2119567691","https://openalex.org/W2155153696","https://openalex.org/W2168359464","https://openalex.org/W2236244207","https://openalex.org/W2482498454","https://openalex.org/W2553297237","https://openalex.org/W2567455162","https://openalex.org/W2769112066","https://openalex.org/W2787666871","https://openalex.org/W2926786214","https://openalex.org/W2963488340","https://openalex.org/W2964241534","https://openalex.org/W2979289616","https://openalex.org/W2982200588","https://openalex.org/W2989847975","https://openalex.org/W3097575142","https://openalex.org/W3118210634","https://openalex.org/W3176760670","https://openalex.org/W4285238035","https://openalex.org/W6774858212"],"related_works":["https://openalex.org/W3035642820","https://openalex.org/W2984671263","https://openalex.org/W4303449484","https://openalex.org/W4200511449","https://openalex.org/W2961085424","https://openalex.org/W4306321456","https://openalex.org/W2134289401","https://openalex.org/W3196155444","https://openalex.org/W4285046548","https://openalex.org/W4319083788"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}
