{"id":"https://openalex.org/W2104228245","doi":"https://doi.org/10.1109/adprl.2011.5967363","title":"Protecting against evaluation overfitting in empirical reinforcement learning","display_name":"Protecting against evaluation overfitting in empirical reinforcement learning","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2104228245","doi":"https://doi.org/10.1109/adprl.2011.5967363","mag":"2104228245"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2011.5967363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","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/A5056879203","display_name":"Shimon Whiteson","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Shimon Whiteson","raw_affiliation_strings":["Informatics Institute, University of Amsterdam, Netherlands","Informatics Institute University of Amsterdam, the Netherlands"],"affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"Informatics Institute University of Amsterdam, the Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075806019","display_name":"B. K. Tanner","orcid":"https://orcid.org/0000-0002-1474-177X"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Brian Tanner","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Canada","Dept. of Computing Science, Univ. of Alberta, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Dept. of Computing Science, Univ. of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070914351","display_name":"Matthew E. Taylor","orcid":"https://orcid.org/0000-0001-8946-0211"},"institutions":[{"id":"https://openalex.org/I184759092","display_name":"Lafayette College","ror":"https://ror.org/036n0x007","country_code":"US","type":"education","lineage":["https://openalex.org/I184759092"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew E. Taylor","raw_affiliation_strings":["Department of Computer Science, Lafayette College, USA","Department of Computer Science, Lafayette College, , USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Lafayette College, USA","institution_ids":["https://openalex.org/I184759092"]},{"raw_affiliation_string":"Department of Computer Science, Lafayette College, , USA","institution_ids":["https://openalex.org/I184759092"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001594330","display_name":"Peter Stone","orcid":"https://orcid.org/0000-0002-6795-420X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Stone","raw_affiliation_strings":["Department of Computer Science, University of Texas, Austin, USA","Department of Computer Science, University of Texas at Austin, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas, Austin, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056879203"],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":6.14,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.96299664,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9962999820709229,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9948999881744385,"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/overfitting","display_name":"Overfitting","score":0.9535725116729736},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8105521202087402},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7690297365188599},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7163658738136292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6698296070098877},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.5646368265151978},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.538640558719635},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.495760053396225},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1222507655620575},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.08824527263641357},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08758711814880371},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08113855123519897}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9535725116729736},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8105521202087402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7690297365188599},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7163658738136292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6698296070098877},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.5646368265151978},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.538640558719635},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.495760053396225},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1222507655620575},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.08824527263641357},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08758711814880371},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08113855123519897},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/adprl.2011.5967363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/d3e917b4-aba0-4890-999d-e60b3076e4a8","is_oa":false,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/protecting-against-evaluation-overfitting-in-empirical-reinforcement-learning(d3e917b4-aba0-4890-999d-e60b3076e4a8).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Whiteson, S, Tanner, B, Taylor, M E & Stone, P 2011, Protecting against evaluation overfitting in empirical reinforcement learning. in Proceedings of the IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL 2011). pp. 120-127, 2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL 2011), Paris, France, 11/04/11. https://doi.org/10.1109/ADPRL.2011.5967363","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.232.8935","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.232.8935","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://staff.science.uva.nl/%7Ewhiteson/pubs/whitesonadprl11.pdf","raw_type":"text"},{"id":"pmh:oai:dare.uva.nl:publications/d3e917b4-aba0-4890-999d-e60b3076e4a8","is_oa":false,"landing_page_url":"http://dare.uva.nl/personal/pure/en/publications/protecting-against-evaluation-overfitting-in-empirical-reinforcement-learning(d3e917b4-aba0-4890-999d-e60b3076e4a8).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Whiteson, S, Tanner, B, Taylor, M E & Stone, P 2011, Protecting against evaluation overfitting in empirical reinforcement learning. in Proceedings of the IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL 2011). pp. 120-127, 2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL 2011), Paris, France, 11/04/11. https://doi.org/10.1109/ADPRL.2011.5967363","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W40442397","https://openalex.org/W99485931","https://openalex.org/W205252556","https://openalex.org/W1508997545","https://openalex.org/W1517322531","https://openalex.org/W1565746575","https://openalex.org/W1590105591","https://openalex.org/W1606530647","https://openalex.org/W1999632197","https://openalex.org/W2009708807","https://openalex.org/W2015688842","https://openalex.org/W2047177732","https://openalex.org/W2076337359","https://openalex.org/W2079247031","https://openalex.org/W2092993939","https://openalex.org/W2096942889","https://openalex.org/W2097381042","https://openalex.org/W2100483895","https://openalex.org/W2103048296","https://openalex.org/W2104569262","https://openalex.org/W2108949035","https://openalex.org/W2112325195","https://openalex.org/W2112865076","https://openalex.org/W2116459397","https://openalex.org/W2124175081","https://openalex.org/W2136074593","https://openalex.org/W2151023586","https://openalex.org/W2165727990","https://openalex.org/W2169743339","https://openalex.org/W2400138769","https://openalex.org/W3020747880","https://openalex.org/W3104240813","https://openalex.org/W3120740533","https://openalex.org/W4230030242","https://openalex.org/W6608410415","https://openalex.org/W6635481144","https://openalex.org/W6654247662","https://openalex.org/W6674600207","https://openalex.org/W6675223484","https://openalex.org/W6675580330","https://openalex.org/W6678114464","https://openalex.org/W6786155630","https://openalex.org/W6788247690"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W4378510483","https://openalex.org/W4376166922","https://openalex.org/W2490526372","https://openalex.org/W4221142204"],"abstract_inverted_index":{"Empirical":[0],"evaluations":[1,34,61],"play":[2],"an":[3,100],"important":[4],"role":[5],"in":[6,27,59],"machine":[7],"learning.":[8],"However,":[9],"the":[10,17],"usefulness":[11],"of":[12],"any":[13],"evaluation":[14],"depends":[15],"on":[16,64],"empirical":[18,23],"methodology":[19],"employed.":[20],"Designing":[21],"good":[22],"methodologies":[24,97],"is":[25,46],"difficult":[26],"part":[28],"because":[29],"agents":[30],"can":[31,98],"overfit":[32],"test":[33],"and":[35,52],"thereby":[36],"obtain":[37],"misleadingly":[38],"high":[39],"scores.":[40],"We":[41],"argue":[42],"that":[43],"reinforcement":[44],"learning":[45],"particularly":[47],"vulnerable":[48],"to":[49,76],"environment":[50],"overfitting":[51],"propose":[53],"as":[54],"a":[55,69],"remedy":[56],"generalized":[57],"methodologies,":[58],"which":[60],"are":[62],"based":[63],"multiple":[65],"environments":[66,83],"sampled":[67],"from":[68,81],"distribution.":[70],"In":[71],"addition,":[72],"we":[73,90],"consider":[74],"how":[75,95],"summarize":[77],"performance":[78],"when":[79],"scores":[80],"different":[82],"may":[84],"not":[85],"have":[86],"commensurate":[87],"values.":[88],"Finally,":[89],"present":[91],"proof-of-concept":[92],"results":[93],"demonstrating":[94],"these":[96],"validate":[99],"intuitively":[101],"useful":[102],"range-adaptive":[103],"tile":[104],"coding":[105],"method.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":6},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}