{"id":"https://openalex.org/W2136719210","doi":null,"title":"Explorations in efficient reinforcement learning","display_name":"Explorations in efficient reinforcement learning","publication_year":1999,"publication_date":"1999-02-17","ids":{"openalex":"https://openalex.org/W2136719210","mag":"2136719210"},"language":"en","primary_location":{"id":"pmh:oai:dare.uva.nl:openaire/6ac07651-85ee-4c7b-9cab-86eea5b818f4","doi":null,"is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/explorations-in-efficient-reinforcement-learning(6ac07651-85ee-4c7b-9cab-86eea5b818f4).html","pdf_url":"https://pure.uva.nl/ws/files/3153480/8462_UBA003000033_001.pdf","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,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wiering, M 1999, 'Explorations in efficient reinforcement learning', Doctor of Philosophy.","raw_type":"info:eu-repo/semantics/other"},"volume":null,"type":"other","is_traditional":false,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.uva.nl/ws/files/3153480/8462_UBA003000033_001.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060596453","display_name":"Marco Wiering","orcid":"https://orcid.org/0000-0003-4331-7537","observed_orcids":["https://orcid.org/0000-0003-4331-7537"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Marco Wiering","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4331-7537","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5060596453"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":70,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/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"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.9359999895095825},{"id":"https://openalex.org/keywords/sequential-decision-making","display_name":"sequential decision making","score":0.9129999876022339},{"id":"https://openalex.org/keywords/value-function-learning","display_name":"value function learning","score":0.7350000143051147},{"id":"https://openalex.org/keywords/reward-function","display_name":"reward function","score":0.8410000205039978},{"id":"https://openalex.org/keywords/agent-environment-interaction","display_name":"agent-environment interaction","score":0.7369999885559082},{"id":"https://openalex.org/keywords/policy-evaluation","display_name":"policy evaluation","score":0.49300000071525574}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9266544580459595},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6930519342422485},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.6218467950820923},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6046289801597595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5960538387298584},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5524889826774597},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5446533560752869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5276590585708618},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4754906892776489},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.43836674094200134},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4195176661014557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38691771030426025},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2997627854347229},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18921411037445068},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1269519329071045},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09296569228172302},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.06476286053657532},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:dare.uva.nl:openaire/6ac07651-85ee-4c7b-9cab-86eea5b818f4","doi":null,"is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/explorations-in-efficient-reinforcement-learning(6ac07651-85ee-4c7b-9cab-86eea5b818f4).html","pdf_url":"https://pure.uva.nl/ws/files/3153480/8462_UBA003000033_001.pdf","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,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wiering, M 1999, 'Explorations in efficient reinforcement learning', Doctor of Philosophy.","raw_type":"info:eu-repo/semantics/other"},{"id":"pmh:oai:dspace.library.uu.nl:1874/20822","doi":null,"is_oa":true,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/20822","pdf_url":null,"source":{"id":"https://openalex.org/S4306401649","display_name":"Utrecht University Repository (Utrecht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I193662353","host_organization_name":"Utrecht University","host_organization_lineage":["https://openalex.org/I193662353"],"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":null,"raw_type":"Dissertation"},{"id":"pmh:uu:oai:dspace.library.uu.nl:1874/20822","doi":null,"is_oa":true,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/20822","pdf_url":null,"source":{"id":"https://openalex.org/S4306401649","display_name":"Utrecht University Repository (Utrecht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I193662353","host_organization_name":"Utrecht University","host_organization_lineage":["https://openalex.org/I193662353"],"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":"info:eu-repo/semantics/doctoralthesis"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/6ac07651-85ee-4c7b-9cab-86eea5b818f4","doi":null,"is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/explorations-in-efficient-reinforcement-learning(6ac07651-85ee-4c7b-9cab-86eea5b818f4).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"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":"info:eu-repo/semantics/doctoralthesis"},{"id":"mag:2136719210","doi":null,"is_oa":false,"landing_page_url":"https://pure.uva.nl/ws/files/3153478/8461_UBA003000033.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:dare.uva.nl:openaire/6ac07651-85ee-4c7b-9cab-86eea5b818f4","doi":null,"is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/explorations-in-efficient-reinforcement-learning(6ac07651-85ee-4c7b-9cab-86eea5b818f4).html","pdf_url":"https://pure.uva.nl/ws/files/3153480/8462_UBA003000033_001.pdf","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,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wiering, M 1999, 'Explorations in efficient reinforcement learning', Doctor of Philosophy.","raw_type":"info:eu-repo/semantics/other"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2136719210.pdf","grobid_xml":"https://content.openalex.org/works/W2136719210.grobid-xml"},"referenced_works_count":159,"referenced_works":["https://openalex.org/W91121345","https://openalex.org/W131709709","https://openalex.org/W134786152","https://openalex.org/W139877375","https://openalex.org/W166582142","https://openalex.org/W168721823","https://openalex.org/W179648542","https://openalex.org/W180325379","https://openalex.org/W1479911746","https://openalex.org/W1480676279","https://openalex.org/W1486056878","https://openalex.org/W1487219635","https://openalex.org/W1491843047","https://openalex.org/W1497256448","https://openalex.org/W1504212531","https://openalex.org/W1504448809","https://openalex.org/W1504506037","https://openalex.org/W1514875444","https://openalex.org/W1515891729","https://openalex.org/W1521977997","https://openalex.org/W1533058732","https://openalex.org/W1535810436","https://openalex.org/W1539216098","https://openalex.org/W1542941925","https://openalex.org/W1547043565","https://openalex.org/W1547105496","https://openalex.org/W1549353711","https://openalex.org/W1555801537","https://openalex.org/W1558406075","https://openalex.org/W1563317173","https://openalex.org/W1569296262","https://openalex.org/W1571787852","https://openalex.org/W1576452626","https://openalex.org/W1579980382","https://openalex.org/W1580495158","https://openalex.org/W1583833196","https://openalex.org/W1593772383","https://openalex.org/W1594216983","https://openalex.org/W1595483645","https://openalex.org/W1597173708","https://openalex.org/W1600437712","https://openalex.org/W1600813180","https://openalex.org/W1638203394","https://openalex.org/W1640646391","https://openalex.org/W1646707810","https://openalex.org/W1657674574","https://openalex.org/W1687873425","https://openalex.org/W1689445748","https://openalex.org/W1706571876","https://openalex.org/W1754468829","https://openalex.org/W1811026443","https://openalex.org/W1834425246","https://openalex.org/W1863227302","https://openalex.org/W1931792391","https://openalex.org/W1966195676","https://openalex.org/W1966221033","https://openalex.org/W1975655150","https://openalex.org/W1988217924","https://openalex.org/W1989101984","https://openalex.org/W1989137448","https://openalex.org/W1991848143","https://openalex.org/W1993740947","https://openalex.org/W1996833561","https://openalex.org/W1999128321","https://openalex.org/W2005314985","https://openalex.org/W2006650111","https://openalex.org/W2009533501","https://openalex.org/W2024668293","https://openalex.org/W2030021468","https://openalex.org/W2034587361","https://openalex.org/W2036317923","https://openalex.org/W2038374320","https://openalex.org/W2048226872","https://openalex.org/W2049886280","https://openalex.org/W2058879737","https://openalex.org/W2062663664","https://openalex.org/W2064675550","https://openalex.org/W2065087844","https://openalex.org/W2066539191","https://openalex.org/W2072931156","https://openalex.org/W2090747326","https://openalex.org/W2095718113","https://openalex.org/W2097437030","https://openalex.org/W2099257174","https://openalex.org/W2099873296","https://openalex.org/W2100677568","https://openalex.org/W2103019454","https://openalex.org/W2103116581","https://openalex.org/W2103496339","https://openalex.org/W2103626435","https://openalex.org/W2106639887","https://openalex.org/W2107726111","https://openalex.org/W2107941094","https://openalex.org/W2110431754","https://openalex.org/W2112483970","https://openalex.org/W2112836703","https://openalex.org/W2114001875","https://openalex.org/W2114083375","https://openalex.org/W2114451917","https://openalex.org/W2117341272","https://openalex.org/W2121517924","https://openalex.org/W2121846340","https://openalex.org/W2122424512","https://openalex.org/W2124175081","https://openalex.org/W2124684839","https://openalex.org/W2125074935","https://openalex.org/W2126598917","https://openalex.org/W2128084896","https://openalex.org/W2130985368","https://openalex.org/W2131600418","https://openalex.org/W2132304387","https://openalex.org/W2132560759","https://openalex.org/W2133360974","https://openalex.org/W2134293360","https://openalex.org/W2134331967","https://openalex.org/W2137234026","https://openalex.org/W2138178898","https://openalex.org/W2139769245","https://openalex.org/W2144578442","https://openalex.org/W2146598871","https://openalex.org/W2146738023","https://openalex.org/W2147243899","https://openalex.org/W2147750403","https://openalex.org/W2147800946","https://openalex.org/W2148694408","https://openalex.org/W2149043954","https://openalex.org/W2150884987","https://openalex.org/W2151710526","https://openalex.org/W2153353990","https://openalex.org/W2154549708","https://openalex.org/W2154929945","https://openalex.org/W2156150292","https://openalex.org/W2157629899","https://openalex.org/W2158548602","https://openalex.org/W2159920598","https://openalex.org/W2160067530","https://openalex.org/W2160108997","https://openalex.org/W2160371091","https://openalex.org/W2160645305","https://openalex.org/W2163569945","https://openalex.org/W2165131254","https://openalex.org/W2168359464","https://openalex.org/W2169051827","https://openalex.org/W2169528473","https://openalex.org/W2170120409","https://openalex.org/W2170616109","https://openalex.org/W2172414771","https://openalex.org/W2317700292","https://openalex.org/W2548352678","https://openalex.org/W2610686804","https://openalex.org/W2766736793","https://openalex.org/W2798058877","https://openalex.org/W2912185451","https://openalex.org/W3011120880","https://openalex.org/W3121926921","https://openalex.org/W3148194443","https://openalex.org/W3198350258","https://openalex.org/W4212899374","https://openalex.org/W4256451422"],"related_works":["https://openalex.org/W7097976146","https://openalex.org/W4210978335","https://openalex.org/W3118677671","https://openalex.org/W4388759515","https://openalex.org/W3049728571","https://openalex.org/W2172425052","https://openalex.org/W4406665955","https://openalex.org/W7214080680","https://openalex.org/W4285260290","https://openalex.org/W7143777792"],"abstract_inverted_index":{"This":[0],"thesis":[1],"describes":[2],"reinforcement":[3,159],"learning":[4,15,160],"(RL)":[5],"methods":[6,161,183,196],"which":[7,27,60,90,118],"can":[8,139],"solve":[9],"sequential":[10],"decision":[11,21],"\\nmaking":[12],"problems":[13,23,179,192],"by":[14,129],"from":[16],"trial":[17],"and":[18,42,165,180,193],"error.":[19],"Sequential":[20],"making":[22],"are":[24,176],"\\nproblems":[25],"in":[26,74],"an":[28,64,83,101],"artificial":[29],"agent":[30,65,89],"interacts":[31],"with":[32,144],"a":[33,55,111,113,135,152,156,163],"specific":[34,157],"environment":[35],"through":[36],"its":[37],"sensors":[38],"\\n(to":[39],"get":[40],"inputs)":[41],"effectors":[43],"(to":[44],"make":[45],"actions).":[46],"To":[47,109],"measure":[48],"the":[49,88,92,97,124,131,142,145,167],"goodness":[50],"of":[51,172,191],"some":[52],"agent's":[53,102,169],"\\nbehavior,":[54],"reward":[56,94,127],"function":[57,115,154],"is":[58,66,80,116],"used":[59],"determines":[61],"how":[62],"much":[63],"rewarded":[67],"or":[68],"\\npenalized":[69],"for":[70,87,120,155,184,197],"performing":[71],"particular":[72,75],"actions":[73],"environmental":[76],"states.":[77],"The":[78],"goal":[79],"to":[81,107,150],"\\nfind":[82],"action":[84,143],"selection":[85],"policy":[86,103,164],"maximizes":[91],"cumulative":[93,126],"collected":[95,128],"\\nin":[96],"future.":[98],"\\nIn":[99],"RL,":[100],"maps":[104],"sensorbased":[105],"inputs":[106],"actions.":[108],"evaluate":[110],"policy,":[112],"value":[114,136,153],"learned":[117],"returns":[119],"each":[121],"possible":[122],"state":[123],"future":[125],"following":[130],"current":[132],"policy.":[133],"Given":[134],"function,":[137],"we":[138],"simply":[140],"select":[141],"largest":[146],"value.":[147],"In":[148],"order":[149],"learn":[151],"problem,":[158],"simulate":[162],"use":[166],"resulting":[168],"experiences":[170],"consisting":[171],"<state,action,reward,next-state>":[173],"quadruples.":[174],"There":[175],"different":[177,181,189],"RL":[178,182],"solving":[185,198],"them.":[186,199],"We":[187],"describe":[188],"categories":[190],"introduce":[194],"new":[195]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":9}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}