{"id":"https://openalex.org/W2141514599","doi":"https://doi.org/10.1109/adprl.2011.5967379","title":"On learning with imperfect representations","display_name":"On learning with imperfect representations","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2141514599","doi":"https://doi.org/10.1109/adprl.2011.5967379","mag":"2141514599"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2011.5967379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967379","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/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":["Department of Computer Science, University of Texas, Austin, Austin, TX, USA","Department of Computer Science, The University of Texas at Austin, 1616 Guadalupe St Suite 2.408 78701 USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas, Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Science, The University of Texas at Austin, 1616 Guadalupe St Suite 2.408 78701 USA","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":["Department of Computer Science, University of Texas, Austin, Austin, TX, USA","Department of Computer Science, The University of Texas at Austin, 1616 Guadalupe St Suite 2.408 78701 USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas, Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Science, The University of Texas at Austin, 1616 Guadalupe St Suite 2.408 78701 USA","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":2.6415,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.9103073,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"27","issue":null,"first_page":"17","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":0.9944000244140625,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9941999912261963,"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/computer-science","display_name":"Computer science","score":0.7453880310058594},{"id":"https://openalex.org/keywords/introspection","display_name":"Introspection","score":0.7299367785453796},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.6599487662315369},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6134557127952576},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.536711573600769},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5143524408340454},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4796767234802246},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.47649091482162476},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4702757000923157},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44358205795288086},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4111374318599701},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.14678984880447388},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.13467419147491455},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10396233201026917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7453880310058594},{"id":"https://openalex.org/C129671850","wikidata":"https://www.wikidata.org/wiki/Q210501","display_name":"Introspection","level":2,"score":0.7299367785453796},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.6599487662315369},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6134557127952576},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.536711573600769},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5143524408340454},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4796767234802246},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.47649091482162476},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4702757000923157},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44358205795288086},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4111374318599701},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.14678984880447388},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.13467419147491455},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10396233201026917},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/adprl.2011.5967379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967379","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:CiteSeerX.psu:10.1.1.190.9847","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.190.9847","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/%7Eshivaram/papers/ks_adprl_2011.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.3762","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.3762","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/~pstone/Papers/bib2html-links/ADPRL11-shivaram.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310620","display_name":"University of Texas at Austin","ror":"https://ror.org/00hj54h04"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":132,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W27992807","https://openalex.org/W32403112","https://openalex.org/W51508254","https://openalex.org/W91593682","https://openalex.org/W158205031","https://openalex.org/W252213970","https://openalex.org/W1262227701","https://openalex.org/W1484499605","https://openalex.org/W1537100889","https://openalex.org/W1540462738","https://openalex.org/W1550698229","https://openalex.org/W1552830313","https://openalex.org/W1555801537","https://openalex.org/W1563127062","https://openalex.org/W1568042657","https://openalex.org/W1576452626","https://openalex.org/W1583380718","https://openalex.org/W1585546214","https://openalex.org/W1597303641","https://openalex.org/W1600046456","https://openalex.org/W1758031947","https://openalex.org/W1778554682","https://openalex.org/W1965227651","https://openalex.org/W1998172110","https://openalex.org/W2009303086","https://openalex.org/W2011418219","https://openalex.org/W2039439610","https://openalex.org/W2045491133","https://openalex.org/W2052117683","https://openalex.org/W2072054128","https://openalex.org/W2072931156","https://openalex.org/W2075268401","https://openalex.org/W2097581696","https://openalex.org/W2099873296","https://openalex.org/W2099945315","https://openalex.org/W2100677568","https://openalex.org/W2100787464","https://openalex.org/W2103626435","https://openalex.org/W2104578628","https://openalex.org/W2105336508","https://openalex.org/W2108734173","https://openalex.org/W2109008048","https://openalex.org/W2109910161","https://openalex.org/W2110962519","https://openalex.org/W2110972482","https://openalex.org/W2116339921","https://openalex.org/W2117341272","https://openalex.org/W2118318536","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2122659384","https://openalex.org/W2123651102","https://openalex.org/W2124175081","https://openalex.org/W2125074935","https://openalex.org/W2125612430","https://openalex.org/W2128630570","https://openalex.org/W2129670787","https://openalex.org/W2129750485","https://openalex.org/W2130801532","https://openalex.org/W2132351269","https://openalex.org/W2132713246","https://openalex.org/W2139418546","https://openalex.org/W2140219596","https://openalex.org/W2141559645","https://openalex.org/W2145680191","https://openalex.org/W2147148915","https://openalex.org/W2148067905","https://openalex.org/W2148150594","https://openalex.org/W2150339816","https://openalex.org/W2151661095","https://openalex.org/W2153192722","https://openalex.org/W2154641875","https://openalex.org/W2155027007","https://openalex.org/W2160308170","https://openalex.org/W2160519132","https://openalex.org/W2161966552","https://openalex.org/W2164056559","https://openalex.org/W2167390657","https://openalex.org/W2169022337","https://openalex.org/W2336687883","https://openalex.org/W2341171179","https://openalex.org/W2489939061","https://openalex.org/W2586680856","https://openalex.org/W2914775474","https://openalex.org/W2997026295","https://openalex.org/W3041202696","https://openalex.org/W3103182070","https://openalex.org/W3139377883","https://openalex.org/W3147501999","https://openalex.org/W4214717370","https://openalex.org/W4243421009","https://openalex.org/W4245296547","https://openalex.org/W4248400504","https://openalex.org/W4253365321","https://openalex.org/W4285719527","https://openalex.org/W4307347247","https://openalex.org/W4324106947","https://openalex.org/W6600556750","https://openalex.org/W6601135396","https://openalex.org/W6602057636","https://openalex.org/W6603745846","https://openalex.org/W6609508172","https://openalex.org/W6634919779","https://openalex.org/W6635798015","https://openalex.org/W6638026421","https://openalex.org/W6638058698","https://openalex.org/W6674711614","https://openalex.org/W6674739337","https://openalex.org/W6675698164","https://openalex.org/W6676744960","https://openalex.org/W6677193802","https://openalex.org/W6677347465","https://openalex.org/W6677834374","https://openalex.org/W6677949083","https://openalex.org/W6678029071","https://openalex.org/W6678114464","https://openalex.org/W6678545291","https://openalex.org/W6679257226","https://openalex.org/W6679406266","https://openalex.org/W6679559434","https://openalex.org/W6681804199","https://openalex.org/W6681933737","https://openalex.org/W6682567211","https://openalex.org/W6683204974","https://openalex.org/W6683472505","https://openalex.org/W6683603353","https://openalex.org/W6684199269","https://openalex.org/W6684586519","https://openalex.org/W6685054274","https://openalex.org/W6786397483","https://openalex.org/W6793692152"],"related_works":["https://openalex.org/W4387404794","https://openalex.org/W2380479582","https://openalex.org/W4387405288","https://openalex.org/W4387404506","https://openalex.org/W2084234399","https://openalex.org/W4387405632","https://openalex.org/W162955351","https://openalex.org/W2368350589","https://openalex.org/W1969578672","https://openalex.org/W2484848127"],"abstract_inverted_index":{"In":[0,132],"this":[1,82,157],"paper":[2,84],"we":[3,79,134],"present":[4,80],"a":[5,21,127,148,154],"perspective":[6],"on":[7],"the":[8,31,69,136],"relationship":[9],"between":[10],"learning":[11,73,89,121,144],"and":[12,47,54,109,125],"representation":[13,34],"in":[14,37,74,81,87,112,123,142],"sequential":[15],"decision":[16],"making":[17],"tasks.":[18],"We":[19,115,146],"undertake":[20],"brief":[22],"survey":[23],"of":[24,52,71,138,150],"existing":[25],"real-world":[26],"applications,":[27],"which":[28],"demonstrates":[29],"that":[30,86],"classical":[32],"\u201ctabular\u201d":[33],"seldom":[35],"applies":[36],"practice.":[38,75],"Specifically,":[39],"several":[40],"practical":[41],"tasks":[42],"suffer":[43],"from":[44],"state":[45],"aliasing,":[46],"most":[48],"demand":[49],"some":[50],"form":[51],"generalization":[53],"function":[55],"approximation.":[56],"Coping":[57],"with":[58,95],"these":[59],"representational":[60],"aspects":[61],"thus":[62],"becomes":[63],"an":[64,117],"important":[65],"direction":[66],"for":[67,106,120,129,156],"furthering":[68],"advent":[70],"reinforcement":[72],"The":[76],"central":[77],"thesis":[78],"position":[83],"is":[85],"practice,":[88,124],"methods":[90,122],"specifically":[91],"developed":[92,105],"to":[93,100],"work":[94],"imperfect":[96],"representations":[97,108],"are":[98],"likely":[99],"perform":[101],"better":[102],"than":[103],"those":[104],"perfect":[107],"then":[110],"applied":[111],"imperfect-representation":[113],"settings.":[114],"specify":[116],"evaluation":[118],"criterion":[119],"propose":[126],"framework":[128],"their":[130],"synthesis.":[131],"particular,":[133],"highlight":[135],"degrees":[137],"\u201crepresentational":[139],"bias\u201d":[140],"prevalent":[141],"different":[143],"methods.":[145],"reference":[147],"variety":[149],"relevant":[151],"literature":[152],"as":[153],"background":[155],"introspective":[158],"essay.":[159]},"counts_by_year":[{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}