{"id":"https://openalex.org/W2142916680","doi":"https://doi.org/10.2478/s13230-010-0002-4","title":"Exploring Parameter Space in Reinforcement Learning","display_name":"Exploring Parameter Space in Reinforcement Learning","publication_year":2010,"publication_date":"2010-03-01","ids":{"openalex":"https://openalex.org/W2142916680","doi":"https://doi.org/10.2478/s13230-010-0002-4","mag":"2142916680"},"language":"en","primary_location":{"id":"doi:10.2478/s13230-010-0002-4","is_oa":true,"landing_page_url":"https://doi.org/10.2478/s13230-010-0002-4","pdf_url":"https://www.degruyter.com/document/doi/10.2478/s13230-010-0002-4/pdf","source":{"id":"https://openalex.org/S4210226531","display_name":"Paladyn Journal of Behavioral Robotics","issn_l":"2080-9778","issn":["2080-9778","2081-4836"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320322","host_organization_name":"De Gruyter Open","host_organization_lineage":["https://openalex.org/P4310320322","https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter Open","De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Paladyn, Journal of Behavioral Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.degruyter.com/document/doi/10.2478/s13230-010-0002-4/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061358849","display_name":"Thomas R\u00fcckstie\u00df","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Thomas R\u00fcckstie\u00df","raw_affiliation_strings":["Technische Universit\u00e4t M\u00fcnchen, Institut f\u00fcr Informatik VI, Boltzmannstr. 3, 85748 Garching, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t M\u00fcnchen, Institut f\u00fcr Informatik VI, Boltzmannstr. 3, 85748 Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060472610","display_name":"Frank Sehnke","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frank Sehnke","raw_affiliation_strings":["Technische Universit\u00e4t M\u00fcnchen, Institut f\u00fcr Informatik VI, Boltzmannstr. 3, 85748 Garching, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t M\u00fcnchen, Institut f\u00fcr Informatik VI, Boltzmannstr. 3, 85748 Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081322018","display_name":"Tom Schaul","orcid":"https://orcid.org/0000-0002-2961-8782"},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Tom Schaul","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence (IDSIA), Galleria 2, 6928 Manno-Lugano, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence (IDSIA), Galleria 2, 6928 Manno-Lugano, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053990531","display_name":"Daan Wierstra","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Daan Wierstra","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence (IDSIA), Galleria 2, 6928 Manno-Lugano, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence (IDSIA), Galleria 2, 6928 Manno-Lugano, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100650176","display_name":"Yi Sun","orcid":"https://orcid.org/0000-0002-8019-6765"},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Yi Sun","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence (IDSIA), Galleria 2, 6928 Manno-Lugano, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence (IDSIA), Galleria 2, 6928 Manno-Lugano, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071172037","display_name":"J\u00fcrgen Schmidhuber","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"J\u00fcrgen Schmidhuber","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence (IDSIA), Galleria 2, 6928 Manno-Lugano, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence (IDSIA), Galleria 2, 6928 Manno-Lugano, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061358849"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":{"value":1000,"currency":"EUR","value_usd":1078},"apc_paid":{"value":1000,"currency":"EUR","value_usd":1078},"fwci":14.2349,"has_fulltext":true,"cited_by_count":79,"citation_normalized_percentile":{"value":0.98915721,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"1","issue":"1","first_page":"14","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994000196456909,"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/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8422955870628357},{"id":"https://openalex.org/keywords/parameter-space","display_name":"Parameter space","score":0.7097000479698181},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6922280788421631},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5355446338653564},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.45075154304504395},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.441601037979126},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43729168176651},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4240574538707733},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19814914464950562}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8422955870628357},{"id":"https://openalex.org/C73586568","wikidata":"https://www.wikidata.org/wiki/Q2600211","display_name":"Parameter space","level":2,"score":0.7097000479698181},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6922280788421631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5355446338653564},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.45075154304504395},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.441601037979126},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43729168176651},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4240574538707733},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19814914464950562},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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":6,"locations":[{"id":"doi:10.2478/s13230-010-0002-4","is_oa":true,"landing_page_url":"https://doi.org/10.2478/s13230-010-0002-4","pdf_url":"https://www.degruyter.com/document/doi/10.2478/s13230-010-0002-4/pdf","source":{"id":"https://openalex.org/S4210226531","display_name":"Paladyn Journal of Behavioral Robotics","issn_l":"2080-9778","issn":["2080-9778","2081-4836"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320322","host_organization_name":"De Gruyter Open","host_organization_lineage":["https://openalex.org/P4310320322","https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter Open","De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Paladyn, Journal of Behavioral Robotics","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.189.2622","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.189.2622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idsia.ch/%7Etom/publications/paladyn.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.296.3604","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.296.3604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idsia.ch/~tom/publications/paladyn.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.300.2671","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.300.2671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idsia.ch/~juergen/paladyn2010.pdf","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:1d7d7f4ee4c14115b57878db43f50fab","is_oa":true,"landing_page_url":"https://doaj.org/article/1d7d7f4ee4c14115b57878db43f50fab","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Paladyn, Vol 1, Iss 1, Pp 14-24 (2010)","raw_type":"article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1287478","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1287478","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"doi:10.2478/s13230-010-0002-4","is_oa":true,"landing_page_url":"https://doi.org/10.2478/s13230-010-0002-4","pdf_url":"https://www.degruyter.com/document/doi/10.2478/s13230-010-0002-4/pdf","source":{"id":"https://openalex.org/S4210226531","display_name":"Paladyn Journal of Behavioral Robotics","issn_l":"2080-9778","issn":["2080-9778","2081-4836"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320322","host_organization_name":"De Gruyter Open","host_organization_lineage":["https://openalex.org/P4310320322","https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter Open","De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Paladyn, Journal of Behavioral Robotics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2142916680.pdf","grobid_xml":"https://content.openalex.org/works/W2142916680.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W65193931","https://openalex.org/W166862392","https://openalex.org/W584392662","https://openalex.org/W1176136657","https://openalex.org/W1487219635","https://openalex.org/W1540706608","https://openalex.org/W1557517019","https://openalex.org/W1594871463","https://openalex.org/W1595159159","https://openalex.org/W1952489873","https://openalex.org/W1959983357","https://openalex.org/W2027964569","https://openalex.org/W2089933214","https://openalex.org/W2101539915","https://openalex.org/W2112036188","https://openalex.org/W2116468180","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2123327324","https://openalex.org/W2127107099","https://openalex.org/W2130990842","https://openalex.org/W2137104525","https://openalex.org/W2138537392","https://openalex.org/W2142508340","https://openalex.org/W2143803054","https://openalex.org/W2146737184","https://openalex.org/W2152195021","https://openalex.org/W2155027007","https://openalex.org/W2157701998","https://openalex.org/W2160723927","https://openalex.org/W2166160300","https://openalex.org/W2172968643","https://openalex.org/W2402846924","https://openalex.org/W2414365832","https://openalex.org/W2543580944","https://openalex.org/W3133056632","https://openalex.org/W4214717370","https://openalex.org/W4214807090","https://openalex.org/W4230563027","https://openalex.org/W4247982840","https://openalex.org/W6640954454","https://openalex.org/W6679563851","https://openalex.org/W6680108847","https://openalex.org/W6682262322","https://openalex.org/W6682642761"],"related_works":["https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W3037422413","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W4306674287","https://openalex.org/W3111983280","https://openalex.org/W4319083788"],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2],"discusses":[3],"parameter-based":[4],"exploration":[5,29,78,88],"methods":[6,11],"for":[7],"reinforcement":[8,31],"learning.":[9],"Parameter-based":[10,28],"perturb":[12],"parameters":[13],"of":[14],"a":[15,76],"general":[16],"function":[17],"approximator":[18],"directly,":[19],"rather":[20],"than":[21],"adding":[22],"noise":[23],"to":[24,86],"the":[25],"resulting":[26],"actions.":[27],"unifies":[30],"learning":[32],"and":[33,36,52],"black-box":[34],"optimization,":[35],"has":[37],"several":[38,63],"advantages":[39],"over":[40],"action":[41],"perturbation.":[42],"We":[43],"review":[44],"two":[45],"recent":[46],"parameter-exploring":[47],"algorithms:":[48],"Natural":[49],"Evolution":[50],"Strategies":[51],"Policy":[53],"Gradients":[54],"with":[55],"Parameter-Based":[56],"Exploration.":[57],"Both":[58],"outperform":[59],"state-of-the-art":[60],"algorithms":[61,85],"in":[62,69,89],"complex":[64],"high-dimensional":[65],"tasks":[66],"commonly":[67],"found":[68],"robot":[70],"control.":[71],"Furthermore,":[72],"we":[73],"describe":[74],"how":[75],"novel":[77],"method,":[79],"State-Dependent":[80],"Exploration,":[81],"can":[82],"modify":[83],"existing":[84],"mimic":[87],"parameter":[90],"space.":[91]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":11}],"updated_date":"2026-07-07T14:30:12.667765","created_date":"2025-10-10T00:00:00"}
