{"id":"https://openalex.org/W2160308170","doi":"https://doi.org/10.1145/1329125.1329241","title":"Batch reinforcement learning in a complex domain","display_name":"Batch reinforcement learning in a complex domain","publication_year":2007,"publication_date":"2007-05-14","ids":{"openalex":"https://openalex.org/W2160308170","doi":"https://doi.org/10.1145/1329125.1329241","mag":"2160308170"},"language":"en","primary_location":{"id":"doi:10.1145/1329125.1329241","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1329125.1329241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems","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/A5038200034","display_name":"Shivaram Kalyanakrishnan","orcid":null},"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":true,"raw_author_name":"Shivaram Kalyanakrishnan","raw_affiliation_strings":["The University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"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":["The University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5038200034"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":5.3126,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.9558068,"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.994700014591217,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.991100013256073,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9232288599014282},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7820179462432861},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.6664620041847229},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.6486750245094299},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5612545013427734},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5158323645591736},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4996628761291504},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.49384552240371704},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4363555908203125},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.41599828004837036},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11383157968521118}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9232288599014282},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7820179462432861},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.6664620041847229},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.6486750245094299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5612545013427734},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5158323645591736},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4996628761291504},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49384552240371704},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4363555908203125},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.41599828004837036},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11383157968521118},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1329125.1329241","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1329125.1329241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.8738","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.8738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/users/shivaram/papers/ks_aamas_2007.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.78.8431","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.78.8431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/users/pstone/Papers/bib2html-links/AAMAS07-kalyanakrishnan.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1457556245","display_name":null,"funder_award_id":"EIA-0303609","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3402348735","display_name":null,"funder_award_id":"IIS-0237699","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"},{"id":"https://openalex.org/G8664215970","display_name":null,"funder_award_id":"HR0011-04-1-0035","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332169","display_name":"Directorate for Computer and Information Science and Engineering","ror":"https://ror.org/025kzpk63"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W166862392","https://openalex.org/W1517018472","https://openalex.org/W1585603966","https://openalex.org/W1760981091","https://openalex.org/W2104641222","https://openalex.org/W2108734173","https://openalex.org/W2109910161","https://openalex.org/W2119053738","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2126565096","https://openalex.org/W2141559645","https://openalex.org/W2141754131","https://openalex.org/W2169659168","https://openalex.org/W2612972698","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3006656721","https://openalex.org/W3139377883","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W2877093712","https://openalex.org/W4308828368","https://openalex.org/W2116157560","https://openalex.org/W1528400370"],"abstract_inverted_index":{"Temporal":[0],"difference":[1],"reinforcement":[2,62,120],"learning":[3,55,63,121],"algorithms":[4,122,125],"are":[5,32],"perfectly":[6],"suited":[7],"to":[8,70,84,87],"autonomous":[9],"agents":[10],"because":[11],"they":[12,51],"learn":[13],"directly":[14],"from":[15],"an":[16],"agent's":[17],"experience":[18,39,77],"based":[19,126],"on":[20,65,99,127],"sequential":[21],"actions":[22],"in":[23,35,42,82,96,131,161],"the":[24,66,88,97,145],"environment.":[25],"However,":[26],"their":[27,36,128],"most":[28],"common":[29],"algorithmic":[30],"variants":[31],"relatively":[33],"inefficient":[34],"use":[37],"of":[38],"data,":[40],"which":[41],"many":[43],"agent-based":[44],"settings":[45],"can":[46],"be":[47],"scarce.":[48],"In":[49,112],"particular,":[50],"make":[52,85],"just":[53],"one":[54],"\"update\"":[56],"for":[57],"each":[58],"atomic":[59],"experience.":[60],"Batch":[61],"algorithms,":[64],"other":[67],"hand,":[68],"aim":[69],"achieve":[71],"greater":[72],"data":[73,78],"efficiency":[74],"by":[75],"saving":[76],"and":[79,105,117,153],"using":[80],"it":[81],"aggregate":[83],"updates":[86],"learned":[89],"policy.":[90],"Their":[91],"success":[92],"has":[93],"been":[94],"demonstrated":[95],"past":[98],"simple":[100],"domains":[101],"like":[102,109],"grid":[103],"worlds":[104],"low-dimensional":[106],"control":[107],"applications":[108],"pole":[110],"balancing.":[111],"this":[113],"paper,":[114],"we":[115,149],"compare":[116],"contrast":[118],"batch":[119,147],"with":[123],"on-line":[124],"empirical":[129],"performance":[130],"a":[132],"complex,":[133],"continuous,":[134],"noisy,":[135],"multiagent":[136],"domain,":[137],"namely":[138],"RoboCup":[139],"soccer":[140],"Keepaway.":[141],"We":[142],"find":[143],"that":[144],"two":[146],"methods":[148],"consider,":[150],"Experience":[151],"Replay":[152],"Fitted":[154],"Q":[155],"Iteration,":[156],"both":[157],"yield":[158],"significant":[159],"gains":[160],"sample":[162],"complexity,":[163],"while":[164],"achieving":[165],"high":[166],"asymptotic":[167],"performance.":[168]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}