{"id":"https://openalex.org/W314779054","doi":null,"title":"Learning of non-parametric control policies with high-dimensional state features","display_name":"Learning of non-parametric control policies with high-dimensional state features","publication_year":2015,"publication_date":"2015-05-12","ids":{"openalex":"https://openalex.org/W314779054","mag":"314779054"},"language":"en","primary_location":{"id":"pmh:oai:eprints.lincoln.ac.uk:25757","doi":null,"is_oa":true,"landing_page_url":"http://eprints.lincoln.ac.uk/id/eprint/25757/1/vanhoof15.pdf","pdf_url":"http://eprints.lincoln.ac.uk/id/eprint/25757/1/vanhoof15.pdf","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},"parent_works":[],"lineage":["https://openalex.org/W314779054"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://eprints.lincoln.ac.uk/id/eprint/25757/1/vanhoof15.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057277609","display_name":"Herke van Hoof","orcid":"https://orcid.org/0000-0002-1583-3692","observed_orcids":["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 Hoof","raw_affiliation_strings":["Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1583-3692","affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt, 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","observed_orcids":["https://orcid.org/0000-0002-5266-8091"]},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"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":["Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society"],"raw_orcid":"https://orcid.org/0000-0002-5266-8091","affiliations":[{"raw_affiliation_string":"Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society","institution_ids":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110467801","display_name":"Gerhard M. Neumann","orcid":"https://orcid.org/0000-0002-5483-4225","observed_orcids":["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":["Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5483-4225","affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.45,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.94885917,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":99},"biblio":{"volume":"38","issue":null,"first_page":"995","last_page":"1003"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/policy-search","display_name":"policy search","score":0.6639999747276306},{"id":"https://openalex.org/keywords/kernel-embedding","display_name":"kernel embedding","score":0.7770000100135803},{"id":"https://openalex.org/keywords/infinite-horizon-control","display_name":"infinite horizon control","score":0.6190000176429749},{"id":"https://openalex.org/keywords/visual-servoing","display_name":"visual servoing","score":0.6899999976158142}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7802742719650269},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7343979477882385},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5534402132034302},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5484682321548462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5336122512817383},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5052099823951721},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.4994385242462158},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4938538670539856},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4886360764503479},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.4428442716598511},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.43617427349090576},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.43156105279922485},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41942569613456726},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3932928740978241},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3125648498535156},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.26161545515060425},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15601268410682678},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:eprints.lincoln.ac.uk:25757","doi":null,"is_oa":true,"landing_page_url":"http://eprints.lincoln.ac.uk/id/eprint/25757/1/vanhoof15.pdf","pdf_url":"http://eprints.lincoln.ac.uk/id/eprint/25757/1/vanhoof15.pdf","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:figshare.com:article/24361264","doi":null,"is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Learning_of_non-parametric_control_policies_with_high-dimensional_state_features/24361264","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,"listed_in":[],"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":null,"raw_type":"Text"},{"id":"pmh:oai:pure.mpg.de:item_2261004","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/11858/00-001M-0000-002A-20A1-6","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,"listed_in":[],"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":"JMLR: Workshop and Conference Proceedings","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:314779054","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v38/vanhoof15.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419146","display_name":"International Conference on Artificial Intelligence and Statistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Artificial Intelligence and Statistics","raw_type":null}],"best_oa_location":{"id":"pmh:oai:eprints.lincoln.ac.uk:25757","doi":null,"is_oa":true,"landing_page_url":"http://eprints.lincoln.ac.uk/id/eprint/25757/1/vanhoof15.pdf","pdf_url":"http://eprints.lincoln.ac.uk/id/eprint/25757/1/vanhoof15.pdf","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5468754129","display_name":"Composing Learning for Artificial Cognitive Systems","funder_award_id":"270327","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5904448303","display_name":"Tactile Manipulation","funder_award_id":"610967","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W314779054.pdf","grobid_xml":"https://content.openalex.org/works/W314779054.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W199564175","https://openalex.org/W1499669280","https://openalex.org/W1540155273","https://openalex.org/W1543510660","https://openalex.org/W1898511152","https://openalex.org/W1929309940","https://openalex.org/W2001095967","https://openalex.org/W2077933344","https://openalex.org/W2088038240","https://openalex.org/W2117481033","https://openalex.org/W2123979492","https://openalex.org/W2130005627","https://openalex.org/W2131904374","https://openalex.org/W2149860990","https://openalex.org/W2150234726","https://openalex.org/W2160536246","https://openalex.org/W2162427161","https://openalex.org/W2164056559","https://openalex.org/W2578657880"],"related_works":["https://openalex.org/W2751302235","https://openalex.org/W4415342849","https://openalex.org/W1191599655","https://openalex.org/W141699348","https://openalex.org/W4229063289","https://openalex.org/W2730929966","https://openalex.org/W1550946783","https://openalex.org/W2272321391","https://openalex.org/W2271263738","https://openalex.org/W3125539274"],"abstract_inverted_index":{"Learning":[0],"complex":[1],"control":[2],"policies":[3,55],"from":[4,83],"highdimensional":[5],"sensory":[6],"input":[7],"is":[8],"a":[9,39],"challenge":[10],"forreinforcement":[11],"learning":[12],"algorithms.":[13],"Kernel":[14],"methods":[15],"that":[16,66],"approximate":[17],"values":[18],"functionsor":[19],"transition":[20],"models":[21],"can":[22,52,75],"address":[23],"this":[24,35],"problem.":[25],"Yet,":[26],"many":[27],"current":[28],"approaches":[29],"rely":[30],"oninstable":[31],"greedy":[32],"maximization.":[33],"In":[34],"paper,":[36],"we":[37],"develop":[38],"policy":[40,45],"search":[41],"algorithm":[42,74],"thatintegrates":[43],"robust":[44],"updates":[46],"and":[47],"kernel":[48],"embeddings.":[49],"Our":[50],"method":[51,68],"learn":[53,76],"nonparametriccontrol":[54],"for":[56],"infinite":[57],"horizon":[58],"continuous":[59],"MDPs":[60],"with":[61],"high-dimensionalsensory":[62],"representations.":[63],"We":[64],"show":[65],"our":[67,73],"outperforms":[69],"related":[70],"approaches,":[71],"andthat":[72],"an":[77],"underpowered":[78],"swing-up":[79],"task":[80,81],"directly":[82],"highdimensionalimage":[84],"data.":[85]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2016-06-24T00:00:00"}