{"id":"https://openalex.org/W192920577","doi":"https://doi.org/10.1007/978-3-642-27645-3_2","title":"Batch Reinforcement Learning","display_name":"Batch Reinforcement Learning","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W192920577","doi":"https://doi.org/10.1007/978-3-642-27645-3_2","mag":"192920577"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-27645-3_2","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-27645-3_2","pdf_url":null,"source":{"id":"https://openalex.org/S4210169857","display_name":"Adaptation, learning, and optimization","issn_l":"1867-4534","issn":["1867-4534","1867-4542"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptation, Learning, and Optimization","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/A5042382031","display_name":"Sascha Lange","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sascha Lange","raw_affiliation_strings":["Faculty of Engineering, Albert-Ludwigs-Universtit\u00e4t Freiburg, Georges-K\u00f6hler-Allee 079, D-79110, Freiburg, Germany"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Albert-Ludwigs-Universtit\u00e4t Freiburg, Georges-K\u00f6hler-Allee 079, D-79110, Freiburg, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016014514","display_name":"Thomas Gabel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Gabel","raw_affiliation_strings":["Faculty of Engineering, Albert-Ludwigs-Universtit\u00e4t Freiburg, Georges-K\u00f6hler-Allee 079, D-79110, Freiburg, Germany"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Albert-Ludwigs-Universtit\u00e4t Freiburg, Georges-K\u00f6hler-Allee 079, D-79110, Freiburg, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041323275","display_name":"Martin Riedmiller","orcid":"https://orcid.org/0000-0002-8465-5690"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Riedmiller","raw_affiliation_strings":["Faculty of Engineering, Albert-Ludwigs-Universtit\u00e4t Freiburg, Georges-K\u00f6hler-Allee 079, D-79110, Freiburg, Germany"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Albert-Ludwigs-Universtit\u00e4t Freiburg, Georges-K\u00f6hler-Allee 079, D-79110, Freiburg, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042382031"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.6466,"has_fulltext":false,"cited_by_count":382,"citation_normalized_percentile":{"value":0.97216108,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"45","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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":0.9983000159263611,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9902999997138977,"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":0.9894999861717224,"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":0.8965648412704468},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6770663261413574},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6151919364929199},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5701637268066406},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5445050597190857},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5199804902076721},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5021584033966064},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4778006672859192},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4722710847854614},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4518716335296631},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4497138261795044},{"id":"https://openalex.org/keywords/batch-processing","display_name":"Batch processing","score":0.4423341751098633},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17347803711891174},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1376398205757141},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07020658254623413}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8965648412704468},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6770663261413574},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6151919364929199},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5701637268066406},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5445050597190857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5199804902076721},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5021584033966064},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4778006672859192},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4722710847854614},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4518716335296631},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4497138261795044},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.4423341751098633},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17347803711891174},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1376398205757141},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07020658254623413},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-642-27645-3_2","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-27645-3_2","pdf_url":null,"source":{"id":"https://openalex.org/S4210169857","display_name":"Adaptation, learning, and optimization","issn_l":"1867-4534","issn":["1867-4534","1867-4542"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptation, Learning, and Optimization","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.229.787","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.229.787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ml.informatik.uni-freiburg.de/_media/publications/langegabelriedmiller2011chapter.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W34092776","https://openalex.org/W91593682","https://openalex.org/W166862392","https://openalex.org/W186489565","https://openalex.org/W1495288584","https://openalex.org/W1498436455","https://openalex.org/W1538416033","https://openalex.org/W1547105496","https://openalex.org/W1550698229","https://openalex.org/W1560074431","https://openalex.org/W1573503290","https://openalex.org/W1576452626","https://openalex.org/W1646707810","https://openalex.org/W1825869920","https://openalex.org/W2019671144","https://openalex.org/W2088956500","https://openalex.org/W2096018174","https://openalex.org/W2096744569","https://openalex.org/W2099833070","https://openalex.org/W2100495367","https://openalex.org/W2101307636","https://openalex.org/W2103464184","https://openalex.org/W2114537044","https://openalex.org/W2115288602","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2125510930","https://openalex.org/W2127412976","https://openalex.org/W2141559645","https://openalex.org/W2143908786","https://openalex.org/W2144304287","https://openalex.org/W2148024708","https://openalex.org/W2149474583","https://openalex.org/W2151416233","https://openalex.org/W2154032554","https://openalex.org/W2154997814","https://openalex.org/W2155143322","https://openalex.org/W2160308170","https://openalex.org/W2187600643","https://openalex.org/W2309755354","https://openalex.org/W2396672775","https://openalex.org/W2712390606","https://openalex.org/W2911839120","https://openalex.org/W2914656440","https://openalex.org/W3121926921","https://openalex.org/W4214717370","https://openalex.org/W4245296547","https://openalex.org/W4285719527","https://openalex.org/W4307347247","https://openalex.org/W6814762204"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2107890255","https://openalex.org/W2089013912","https://openalex.org/W2106552856","https://openalex.org/W2076061571","https://openalex.org/W2038908348","https://openalex.org/W2072376847","https://openalex.org/W1987513656"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":45},{"year":2023,"cited_by_count":33},{"year":2022,"cited_by_count":44},{"year":2021,"cited_by_count":86},{"year":2020,"cited_by_count":62},{"year":2019,"cited_by_count":29},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}