{"id":"https://openalex.org/W2169743339","doi":"https://doi.org/10.1145/1273496.1273624","title":"Multi-task reinforcement learning","display_name":"Multi-task reinforcement learning","publication_year":2007,"publication_date":"2007-06-20","ids":{"openalex":"https://openalex.org/W2169743339","doi":"https://doi.org/10.1145/1273496.1273624","mag":"2169743339"},"language":"en","primary_location":{"id":"doi:10.1145/1273496.1273624","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1273496.1273624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th international conference on Machine learning","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/A5108355538","display_name":"Aaron Wilson","orcid":null},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aaron Wilson","raw_affiliation_strings":["Oregon State University"],"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030052689","display_name":"Alan Fern","orcid":"https://orcid.org/0000-0001-5851-8935"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan Fern","raw_affiliation_strings":["Oregon State University"],"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055101678","display_name":"Soumya Ray","orcid":"https://orcid.org/0000-0002-6673-6796"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soumya Ray","raw_affiliation_strings":["Oregon State University"],"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014260664","display_name":"Prasad Tadepalli","orcid":"https://orcid.org/0000-0003-2736-3912"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasad Tadepalli","raw_affiliation_strings":["Oregon State University"],"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108355538"],"corresponding_institution_ids":["https://openalex.org/I131249849"],"apc_list":null,"apc_paid":null,"fwci":12.1654,"has_fulltext":false,"cited_by_count":271,"citation_normalized_percentile":{"value":0.98549491,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1015","last_page":"1022"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9955999851226807,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8588036298751831},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7863210439682007},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7804267406463623},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6462129950523376},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6237697005271912},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5971025824546814},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5812478065490723},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5746873617172241},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.41743776202201843},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.41225236654281616},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4033065736293793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12457782030105591}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8588036298751831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7863210439682007},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7804267406463623},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6462129950523376},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6237697005271912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5971025824546814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5812478065490723},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5746873617172241},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.41743776202201843},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41225236654281616},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4033065736293793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12457782030105591},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1273496.1273624","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1273496.1273624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th international conference on Machine learning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8100000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1496855202","https://openalex.org/W1515851193","https://openalex.org/W1582436621","https://openalex.org/W1591803298","https://openalex.org/W2039522160","https://openalex.org/W2071814471","https://openalex.org/W2079247031","https://openalex.org/W2080972498","https://openalex.org/W2106953752","https://openalex.org/W2121863487","https://openalex.org/W2128775537","https://openalex.org/W2132057084","https://openalex.org/W2913668833","https://openalex.org/W4214717370","https://openalex.org/W4237780050"],"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":{"We":[0,29,123],"consider":[1],"the":[2,9,31,48,75,85,105,112,117],"problem":[3],"of":[4,16,77,87,107,119,147],"multi-task":[5],"reinforcement":[6,59],"learning,":[7],"where":[8],"agent":[10],"needs":[11],"to":[12,72,93,96,114,132,137],"solve":[13],"a":[14,24,36,66,88,144],"sequence":[15],"Markov":[17],"Decision":[18],"Processes":[19],"(MDPs)":[20],"chosen":[21],"randomly":[22],"from":[23],"fixed":[25],"but":[26],"unknown":[27],"distribution.":[28],"model":[30,90,113],"distribution":[32,51],"over":[33],"MDPs":[34],"using":[35],"hierarchical":[37,62],"Bayesian":[38,58,63],"infinite":[39,108],"mixture":[40],"model.":[41],"For":[42],"each":[43],"novel":[44],"MDP,":[45],"we":[46,98],"use":[47,86,106],"previously":[49],"learned":[50],"as":[52],"an":[53,138],"informed":[54],"prior":[55,68],"for":[56,111],"modelbased":[57],"learning.":[60],"The":[61],"framework":[64],"provides":[65],"strong":[67],"that":[69,129],"allows":[70,91,110],"us":[71,92],"rapidly":[73],"infer":[74],"characteristics":[76],"new":[78],"environments":[79,97],"based":[80],"on":[81],"previous":[82],"environments,":[83],"while":[84],"nonparametric":[89],"quickly":[94],"adapt":[95],"have":[99],"not":[100],"encountered":[101],"before.":[102],"In":[103],"addition,":[104],"mixtures":[109],"automatically":[115],"learn":[116],"number":[118,146],"underlying":[120],"MDP":[121],"components.":[122],"evaluate":[124],"our":[125],"approach":[126],"and":[127],"show":[128],"it":[130],"leads":[131],"significant":[133],"speedups":[134],"in":[135],"convergence":[136],"optimal":[139],"policy":[140],"after":[141],"observing":[142],"only":[143],"small":[145],"tasks.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":47},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":18},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":20}],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2025-10-10T00:00:00"}