{"id":"https://openalex.org/W2059654640","doi":"https://doi.org/10.1145/1553374.1553426","title":"Hoeffding and Bernstein races for selecting policies in evolutionary direct policy search","display_name":"Hoeffding and Bernstein races for selecting policies in evolutionary direct policy search","publication_year":2009,"publication_date":"2009-06-14","ids":{"openalex":"https://openalex.org/W2059654640","doi":"https://doi.org/10.1145/1553374.1553426","mag":"2059654640"},"language":"en","primary_location":{"id":"doi:10.1145/1553374.1553426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","raw_type":"proceedings-article"},"type":"article","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/A5004382986","display_name":"Verena Heidrich-Meisner","orcid":"https://orcid.org/0000-0003-3502-8778"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Verena Heidrich-Meisner","raw_affiliation_strings":["Institut f\u00fcr Neuroinformatik, Bochum, Germany"],"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Neuroinformatik, Bochum, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042628612","display_name":"Christian Igel","orcid":"https://orcid.org/0000-0003-2868-0856"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian Igel","raw_affiliation_strings":["Institut f\u00fcr Neuroinformatik, Bochum, Germany"],"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Neuroinformatik, Bochum, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004382986"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.4163,"has_fulltext":false,"cited_by_count":117,"citation_normalized_percentile":{"value":0.98979274,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"401","last_page":"408"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9997000098228455,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9997000098228455,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.79706871509552},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6687038540840149},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6116008162498474},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6068732142448425},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5524899363517761},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"Evolutionary computation","score":0.48693811893463135},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.4698794186115265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43505164980888367},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4095385670661926},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40685462951660156},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30447351932525635},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.14268380403518677}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.79706871509552},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6687038540840149},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6116008162498474},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6068732142448425},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5524899363517761},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.48693811893463135},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.4698794186115265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43505164980888367},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4095385670661926},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40685462951660156},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30447351932525635},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.14268380403518677},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1553374.1553426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.159.2144","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.159.2144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.mcgill.ca/~icml2009/papers/229.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W49038156","https://openalex.org/W397102730","https://openalex.org/W1515851193","https://openalex.org/W1519597478","https://openalex.org/W1531201621","https://openalex.org/W1531859564","https://openalex.org/W1564754565","https://openalex.org/W1568161011","https://openalex.org/W1583155004","https://openalex.org/W1585839838","https://openalex.org/W1763200058","https://openalex.org/W1964488926","https://openalex.org/W2097452095","https://openalex.org/W2104578628","https://openalex.org/W2114528843","https://openalex.org/W2116339921","https://openalex.org/W2121863487","https://openalex.org/W2132414174","https://openalex.org/W2138537392","https://openalex.org/W2140671219","https://openalex.org/W2148067905","https://openalex.org/W2165962877","https://openalex.org/W2172968643","https://openalex.org/W2997026295","https://openalex.org/W3013662176","https://openalex.org/W4214717370","https://openalex.org/W4231918628"],"related_works":["https://openalex.org/W51364034","https://openalex.org/W2141938446","https://openalex.org/W2898073868","https://openalex.org/W4284663758","https://openalex.org/W2130703626","https://openalex.org/W4361804730","https://openalex.org/W2142113611","https://openalex.org/W2334467465","https://openalex.org/W2087870008","https://openalex.org/W2162534555"],"abstract_inverted_index":{"Uncertainty":[0],"arises":[1],"in":[2,84],"reinforcement":[3],"learning":[4,97],"from":[5],"various":[6],"sources,":[7],"and":[8,33],"therefore":[9],"it":[10],"is":[11,69,83],"necessary":[12],"to":[13,37,90],"consider":[14],"statistics":[15],"based":[16,30],"on":[17,31],"several":[18],"roll-outs":[19],"for":[20,46,60,74,87],"evaluating":[21],"behavioral":[22],"policies.":[23],"We":[24],"add":[25],"an":[26],"adaptive":[27],"uncertainty":[28,51],"handling":[29,52],"Hoeffding":[32],"empirical":[34],"Bernstein":[35],"races":[36],"the":[38,55,61,88,96,102,105],"CMA-ES,":[39],"a":[40,64,75],"variable":[41],"metric":[42],"evolution":[43],"strategy":[44],"proposed":[45],"direct":[47],"policy":[48],"search.":[49],"The":[50,66],"adjusts":[53],"individually":[54],"number":[56],"of":[57,63,79,104],"episodes":[58],"considered":[59],"evaluation":[62],"policy.":[65],"performance":[67],"estimation":[68],"kept":[70],"just":[71],"accurate":[72],"enough":[73],"sufficiently":[76],"good":[77],"ranking":[78],"candidate":[80],"policies,":[81],"which":[82],"turn":[85],"sufficient":[86],"CMA-ES":[89],"find":[91],"better":[92],"solutions.":[93],"This":[94],"increases":[95],"speed":[98],"as":[99,101],"well":[100],"robustness":[103],"algorithm.":[106]},"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":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":14}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}