{"id":"https://openalex.org/W2186389117","doi":null,"title":"Conjugate Markov Decision Processes","display_name":"Conjugate Markov Decision Processes","publication_year":2011,"publication_date":"2011-06-28","ids":{"openalex":"https://openalex.org/W2186389117","mag":"2186389117"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.230.8715","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.230.8715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-anw.cs.umass.edu/pubs/2011/thomas_b_11.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5066332280","display_name":"Philip S. Thomas","orcid":"https://orcid.org/0000-0002-9904-1800","observed_orcids":["https://orcid.org/0000-0002-9904-1800"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip S. Thomas","raw_affiliation_strings":["Department of Computer Science, University of Massachusetts, Amherst, MA 01002, USA#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-9904-1800","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts, Amherst, MA 01002, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089808068","display_name":"Andrew G. Barto","orcid":"https://orcid.org/0000-0002-3581-1896","observed_orcids":["https://orcid.org/0000-0002-3581-1896"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew G. Barto","raw_affiliation_strings":["Department of Computer Science, University of Massachusetts, Amherst, MA 01002, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts, Amherst, MA 01002, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.5245,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.6990386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"137","last_page":"144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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":0.0003000000142492354,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.00019999999494757503,"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/state-mapping","display_name":"state mapping","score":0.49799999594688416},{"id":"https://openalex.org/keywords/feature-space","display_name":"feature space","score":0.4560000002384186},{"id":"https://openalex.org/keywords/skill-discovery","display_name":"skill discovery","score":0.9950000047683716},{"id":"https://openalex.org/keywords/expected-return-maximization","display_name":"expected return maximization","score":0.8489999771118164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7115716338157654},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5511981844902039},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5505164861679077},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5357410907745361},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.501786470413208},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5016679763793945},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.44086581468582153},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.41510167717933655},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41448450088500977},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39791375398635864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39765238761901855},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38585636019706726},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3751778304576874},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3501259982585907},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23708897829055786},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":"pmh:oai:CiteSeerX.psu:10.1.1.230.8715","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.230.8715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-anw.cs.umass.edu/pubs/2011/thomas_b_11.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.640.1532","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.640.1532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icml-2011.org/papers/134_icmlpaper.pdf","raw_type":"text"},{"id":"mag:2186389117","doi":null,"is_oa":false,"landing_page_url":"http://psthomas.com/papers/Thomas2011a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1543217731","https://openalex.org/W1637456626","https://openalex.org/W1974164873","https://openalex.org/W2099618002","https://openalex.org/W2099833070","https://openalex.org/W2106261932","https://openalex.org/W2109059823","https://openalex.org/W2109910161","https://openalex.org/W2121863487","https://openalex.org/W2139053308","https://openalex.org/W2143435603","https://openalex.org/W2145680191","https://openalex.org/W2145805610","https://openalex.org/W2161795906","https://openalex.org/W2172968643"],"related_works":["https://openalex.org/W7095737303","https://openalex.org/W7096322355","https://openalex.org/W639476619","https://openalex.org/W7097951962","https://openalex.org/W7097126477","https://openalex.org/W7097000842","https://openalex.org/W7096844209","https://openalex.org/W2278959751","https://openalex.org/W28736093","https://openalex.org/W2019342219"],"abstract_inverted_index":{"Many":[0],"open":[1],"problems":[2],"involve":[3],"the":[4,23,67],"search":[5,68],"for":[6,69,81],"a":[7,37,63],"mapping":[8,35,44,71],"that":[9,82],"is":[10],"used":[11,72],"by":[12,73],"an":[13,16,79],"algorithm":[14,75],"solving":[15],"MDP.":[17],"Useful":[18],"mappings":[19,50],"are":[20],"often":[21],"from":[22],"state":[24],"set":[25],"to":[26,36,45,66,77],"some":[27],"other":[28],"set.":[29],"Examples":[30],"include":[31],"representation":[32],"discovery":[33,42],"(a":[34,43],"feature":[38],"space)":[39],"and":[40],"skill":[41,46],"termination":[47],"probabilities).":[48],"Different":[49],"result":[51],"in":[52,85],"algorithms":[53],"achieving":[54],"varying":[55],"expected":[56,87],"returns.":[57],"In":[58],"this":[59],"paper":[60],"we":[61],"present":[62],"novel":[64],"approach":[65],"any":[70,74],"attempting":[76],"solve":[78],"MDP,":[80],"which":[83],"results":[84],"maximum":[86],"return.":[88],"1.":[89]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":8},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2016-06-24T00:00:00"}