{"id":"https://openalex.org/W2735649811","doi":"https://doi.org/10.1007/s10994-017-5657-1","title":"Generalized exploration in policy search","display_name":"Generalized exploration in policy search","publication_year":2017,"publication_date":"2017-07-13","ids":{"openalex":"https://openalex.org/W2735649811","doi":"https://doi.org/10.1007/s10994-017-5657-1","mag":"2735649811"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-017-5657-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-017-5657-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-017-5657-1.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/s10994-017-5657-1.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057277609","display_name":"Herke van Hoof","orcid":"https://orcid.org/0000-0002-1583-3692"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Herke van Hoof","raw_affiliation_strings":["School of Computer Science, McGill University, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0002-1583-3692","affiliations":[{"raw_affiliation_string":"School of Computer Science, McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073193182","display_name":"Daniel Tanneberg","orcid":"https://orcid.org/0000-0002-1363-7970"},"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":"Daniel Tanneberg","raw_affiliation_strings":["Intelligent Autonomous Systems Institute, Technische Universit\u00e4t Darmstadt, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1363-7970","affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems Institute, Technische Universit\u00e4t Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","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":["Intelligent Autonomous Systems Institute, Technische Universit\u00e4t Darmstadt, Darmstadt, Germany","Interdepartmental Robot Learning Lab, Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5266-8091","affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems Institute, Technische Universit\u00e4t Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Interdepartmental Robot Learning Lab, Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210135521"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057277609"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":1.0393,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83052714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"106","issue":"9-10","first_page":"1705","last_page":"1724"},"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":0.9951000213623047,"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":0.9783999919891357,"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":0.7858012914657593},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6365682482719421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.504170298576355},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.49012717604637146},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.48192739486694336},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4647495150566101},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3701171278953552},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21682032942771912}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7858012914657593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6365682482719421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.504170298576355},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.49012717604637146},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.48192739486694336},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4647495150566101},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3701171278953552},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21682032942771912},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10994-017-5657-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-017-5657-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-017-5657-1.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:escidoc.org:escidoc:2577718","is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0001-2550-B","pdf_url":null,"source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:107751","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/107751/","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/s10994-017-5657-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-017-5657-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-017-5657-1.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":[],"awards":[{"id":"https://openalex.org/G1230081602","display_name":null,"funder_award_id":"610967","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320323384","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24"},{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2735649811.pdf","grobid_xml":"https://content.openalex.org/works/W2735649811.grobid-xml"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W314779054","https://openalex.org/W1496855202","https://openalex.org/W1499669280","https://openalex.org/W1507087299","https://openalex.org/W1542595278","https://openalex.org/W1582436621","https://openalex.org/W1583882820","https://openalex.org/W1585861384","https://openalex.org/W1591803298","https://openalex.org/W1925816294","https://openalex.org/W1952489873","https://openalex.org/W1977655452","https://openalex.org/W1984381895","https://openalex.org/W2012036715","https://openalex.org/W2012587148","https://openalex.org/W2071444114","https://openalex.org/W2098524868","https://openalex.org/W2106155860","https://openalex.org/W2107726111","https://openalex.org/W2108535023","https://openalex.org/W2109910161","https://openalex.org/W2111967991","https://openalex.org/W2119678437","https://openalex.org/W2119717200","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2125710232","https://openalex.org/W2128596806","https://openalex.org/W2129017877","https://openalex.org/W2136751544","https://openalex.org/W2137104525","https://openalex.org/W2138309709","https://openalex.org/W2138537392","https://openalex.org/W2139053308","https://openalex.org/W2139394304","https://openalex.org/W2142176084","https://openalex.org/W2142916680","https://openalex.org/W2143803054","https://openalex.org/W2144446635","https://openalex.org/W2144902422","https://openalex.org/W2154032554","https://openalex.org/W2158548602","https://openalex.org/W2167117957","https://openalex.org/W2167647761","https://openalex.org/W2173248099","https://openalex.org/W2245825236","https://openalex.org/W2253991908","https://openalex.org/W2280163991","https://openalex.org/W2442341664","https://openalex.org/W2498991332","https://openalex.org/W2962767126","https://openalex.org/W2963616477","https://openalex.org/W2963830168","https://openalex.org/W2963864421","https://openalex.org/W3103182070","https://openalex.org/W4214717370","https://openalex.org/W4250979948","https://openalex.org/W6629614444","https://openalex.org/W6634907821","https://openalex.org/W6634945376","https://openalex.org/W6653435097","https://openalex.org/W6653548176","https://openalex.org/W6676560026","https://openalex.org/W6677916085","https://openalex.org/W6680606377","https://openalex.org/W6681183203","https://openalex.org/W6681302627","https://openalex.org/W6683443546","https://openalex.org/W6690740874","https://openalex.org/W6695011786"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W20361778"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
