{"id":"https://openalex.org/W2168319199","doi":"https://doi.org/10.1145/1143844.1143883","title":"Qualitative reinforcement learning","display_name":"Qualitative reinforcement learning","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2168319199","doi":"https://doi.org/10.1145/1143844.1143883","mag":"2168319199"},"language":"en","primary_location":{"id":"doi:10.1145/1143844.1143883","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1143844.1143883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Machine learning  - ICML '06","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/A5040720036","display_name":"Arkady Epshteyn","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arkady Epshteyn","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043767069","display_name":"Gerald DeJong","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald DeJong","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.3985,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85786362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"305","last_page":"312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.98089998960495,"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/T11674","display_name":"Sports Analytics and Performance","score":0.980400025844574,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7934379577636719},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.678848385810852},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6746867299079895},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5930765867233276},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5070087909698486},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4930433928966522},{"id":"https://openalex.org/keywords/dominance","display_name":"Dominance (genetics)","score":0.42442527413368225},{"id":"https://openalex.org/keywords/stochastic-dominance","display_name":"Stochastic dominance","score":0.4234578013420105},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.4197857081890106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3988657593727112},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1942213773727417}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7934379577636719},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.678848385810852},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6746867299079895},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5930765867233276},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5070087909698486},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4930433928966522},{"id":"https://openalex.org/C151913843","wikidata":"https://www.wikidata.org/wiki/Q3454555","display_name":"Dominance (genetics)","level":3,"score":0.42442527413368225},{"id":"https://openalex.org/C33252445","wikidata":"https://www.wikidata.org/wiki/Q3713315","display_name":"Stochastic dominance","level":2,"score":0.4234578013420105},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.4197857081890106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3988657593727112},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1942213773727417},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1143844.1143883","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1143844.1143883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Machine learning  - ICML '06","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.73.7503","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.73.7503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uiuc.edu/homes/mrebl/Epshteyn_06a.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.93.4407","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.93.4407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ews.uiuc.edu/~aepshtey/pubs/qual_rl.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1512985530","https://openalex.org/W1515851193","https://openalex.org/W1526512085","https://openalex.org/W1556526813","https://openalex.org/W1769460679","https://openalex.org/W1777239053","https://openalex.org/W1988217924","https://openalex.org/W1989486129","https://openalex.org/W1996625075","https://openalex.org/W1999874108","https://openalex.org/W2012728920","https://openalex.org/W2119567691","https://openalex.org/W2121863487"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4225269853"],"abstract_inverted_index":{"When":[0,25],"the":[1,14,23,31,48,85],"transition":[2,55],"probabilities":[3,56],"and":[4,38,104],"rewards":[5],"of":[6,54,59,88,97],"a":[7,36,44],"Markov":[8],"Decision":[9],"Process":[10],"are":[11],"specified":[12,74],"exactly,":[13],"problem":[15],"can":[16,65],"be":[17,66],"solved":[18],"without":[19],"any":[20],"interaction":[21],"with":[22],"environment.":[24],"no":[26,78],"such":[27,79],"specification":[28],"is":[29,35,81,93],"available,":[30,82],"agent's":[32],"only":[33],"recourse":[34],"long":[37],"potentially":[39],"dangerous":[40],"exploration.":[41,89],"We":[42],"present":[43],"framework":[45],"which":[46],"allows":[47],"expert":[49],"to":[50,68,83],"specify":[51],"imprecise":[52],"knowledge":[53],"in":[57],"terms":[58],"stochastic":[60],"dominance":[61],"constraints.":[62],"Our":[63],"algorithm":[64],"used":[67],"find":[69],"optimal":[70],"policies":[71],"for":[72],"qualitatively":[73],"problems,":[75],"or,":[76],"when":[77],"solution":[80],"decrease":[84],"required":[86],"amount":[87],"The":[90],"algorithm's":[91],"behavior":[92],"demonstrated":[94],"on":[95],"simulations":[96],"two":[98],"classic":[99],"problems:":[100],"mountain":[101],"car":[102],"ascent":[103],"cart":[105],"pole":[106],"balancing.":[107]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}