{"id":"https://openalex.org/W2498991332","doi":"https://doi.org/10.1007/s10994-016-5580-x","title":"Probabilistic inference for determining options in reinforcement learning","display_name":"Probabilistic inference for determining options in reinforcement learning","publication_year":2016,"publication_date":"2016-08-01","ids":{"openalex":"https://openalex.org/W2498991332","doi":"https://doi.org/10.1007/s10994-016-5580-x","mag":"2498991332"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-016-5580-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-016-5580-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-016-5580-x.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-016-5580-x.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047982234","display_name":"Christian Daniel","orcid":"https://orcid.org/0000-0001-7065-5326"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4210156055","display_name":"Robert Bosch (Netherlands)","ror":"https://ror.org/057aydj06","country_code":"NL","type":"company","lineage":["https://openalex.org/I4210156055","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE","NL"],"is_corresponding":true,"raw_author_name":"Christian Daniel","raw_affiliation_strings":["Bosch Corporate Research, Cognitive Systems, Robert-Bosch-Campus 1, 71272, Renningen, Germany","Technische Universit\u00e4t Darmstadt, Hochschulstra\u00dfe 10, 64289, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Bosch Corporate Research, Cognitive Systems, Robert-Bosch-Campus 1, 71272, Renningen, Germany","institution_ids":["https://openalex.org/I4210156055","https://openalex.org/I889804353"]},{"raw_affiliation_string":"Technische Universit\u00e4t Darmstadt, Hochschulstra\u00dfe 10, 64289, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057277609","display_name":"Herke van Hoof","orcid":"https://orcid.org/0000-0002-1583-3692"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Herke van\u00a0Hoof","raw_affiliation_strings":["Technische Universit\u00e4t Darmstadt, Hochschulstra\u00dfe 10, 64289, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Darmstadt, Hochschulstra\u00dfe 10, 64289, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Max-Planck-Institut f\u00fcr Intelligente Systeme, Speemannstra\u00dfe 38, 72076, T\u00fcbingen, Germany","Technische Universit\u00e4t Darmstadt, Hochschulstra\u00dfe 10, 64289, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Max-Planck-Institut f\u00fcr Intelligente Systeme, Speemannstra\u00dfe 38, 72076, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210135521"]},{"raw_affiliation_string":"Technische Universit\u00e4t Darmstadt, Hochschulstra\u00dfe 10, 64289, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110467801","display_name":"Gerhard Neumann","orcid":"https://orcid.org/0000-0002-5483-4225"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Neumann","raw_affiliation_strings":["Technische Universit\u00e4t Darmstadt, Hochschulstra\u00dfe 10, 64289, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Darmstadt, Hochschulstra\u00dfe 10, 64289, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047982234"],"corresponding_institution_ids":["https://openalex.org/I31512782","https://openalex.org/I4210156055","https://openalex.org/I889804353"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":20.7614,"has_fulltext":true,"cited_by_count":93,"citation_normalized_percentile":{"value":0.99314688,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"104","issue":"2-3","first_page":"337","last_page":"357"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9858999848365784,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9781000018119812,"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":0.8463660478591919},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7641050219535828},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7326884269714355},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6043494343757629},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5982989072799683},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5788065195083618},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5391663908958435},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5040901899337769},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.44887757301330566},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.44246453046798706},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4382718801498413},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.36372435092926025},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09945765137672424}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8463660478591919},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7641050219535828},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7326884269714355},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6043494343757629},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5982989072799683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5788065195083618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5391663908958435},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5040901899337769},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.44887757301330566},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.44246453046798706},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4382718801498413},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.36372435092926025},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09945765137672424},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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":5,"locations":[{"id":"doi:10.1007/s10994-016-5580-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-016-5580-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-016-5580-x.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:eprints.lincoln.ac.uk:25739","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196275","display_name":"Lincoln Repository (University of Lincoln)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I51532219","host_organization_name":"University of Lincoln","host_organization_lineage":["https://openalex.org/I51532219"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:figshare.com:article/24361246","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Probabilistic_inference_for_determining_options_in_reinforcement_learning/24361246","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pure.mpg.de:item_2394960","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-002D-19A7-8","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning, Special Issue","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:107782","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/107782/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Artikel"}],"best_oa_location":{"id":"doi:10.1007/s10994-016-5580-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-016-5580-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-016-5580-x.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7900000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2498991332.pdf","grobid_xml":"https://content.openalex.org/works/W2498991332.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W174941419","https://openalex.org/W314779054","https://openalex.org/W1486707268","https://openalex.org/W1494114146","https://openalex.org/W1499669280","https://openalex.org/W1506806321","https://openalex.org/W1507087299","https://openalex.org/W1536990779","https://openalex.org/W1556824961","https://openalex.org/W1557517019","https://openalex.org/W1575431606","https://openalex.org/W1925816294","https://openalex.org/W1949804828","https://openalex.org/W2012392077","https://openalex.org/W2022760091","https://openalex.org/W2071444114","https://openalex.org/W2088038240","https://openalex.org/W2090170171","https://openalex.org/W2097828232","https://openalex.org/W2106261932","https://openalex.org/W2108535023","https://openalex.org/W2109910161","https://openalex.org/W2111967991","https://openalex.org/W2118127869","https://openalex.org/W2119567691","https://openalex.org/W2121517924","https://openalex.org/W2127031267","https://openalex.org/W2130535800","https://openalex.org/W2133853511","https://openalex.org/W2133859362","https://openalex.org/W2139394304","https://openalex.org/W2140801763","https://openalex.org/W2143435603","https://openalex.org/W2158548602","https://openalex.org/W2160371091","https://openalex.org/W2161252410","https://openalex.org/W2167590754","https://openalex.org/W2167647761","https://openalex.org/W2168640731","https://openalex.org/W2211996086","https://openalex.org/W2217025414","https://openalex.org/W2245825236","https://openalex.org/W2334782222","https://openalex.org/W2595840341","https://openalex.org/W4285719527","https://openalex.org/W6653435097","https://openalex.org/W6676560026","https://openalex.org/W6680606377","https://openalex.org/W6680971464","https://openalex.org/W6683821272","https://openalex.org/W6685218902","https://openalex.org/W6690740874"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W2808418668","https://openalex.org/W3096874164","https://openalex.org/W2357975469","https://openalex.org/W2937181779","https://openalex.org/W2145363145","https://openalex.org/W3168977894"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
