{"id":"https://openalex.org/W2133458291","doi":null,"title":"PAC-inspired Option Discovery in Lifelong Reinforcement Learning","display_name":"PAC-inspired Option Discovery in Lifelong Reinforcement Learning","publication_year":2014,"publication_date":"2014-06-21","ids":{"openalex":"https://openalex.org/W2133458291","mag":"2133458291"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.668.6194","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.668.6194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://jmlr.org/proceedings/papers/v32/brunskill14.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/A5084989076","display_name":"Emma Brunskill","orcid":"https://orcid.org/0000-0002-3971-7127","observed_orcids":["https://orcid.org/0000-0002-3971-7127"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emma Brunskill","raw_affiliation_strings":["Computer Science Department, Carnegie Mellon University, Pittsburgh PA 15213"],"raw_orcid":"https://orcid.org/0000-0002-3971-7127","affiliations":[{"raw_affiliation_string":"Computer Science Department, Carnegie Mellon University, Pittsburgh PA 15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107006279","display_name":"Lihong Li","orcid":"https://orcid.org/0000-0002-1264-8483","observed_orcids":["https://orcid.org/0000-0002-1264-8483"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lihong Li","raw_affiliation_strings":["Microsoft Research, One Microsoft way, Redmond, WA 98052"],"raw_orcid":"https://orcid.org/0000-0002-1264-8483","affiliations":[{"raw_affiliation_string":"Microsoft Research, One Microsoft way, Redmond, WA 98052","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6662,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":{"value":0.96186207,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"316","last_page":"324"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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":0.0,"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/options","display_name":"options","score":0.7680000066757202},{"id":"https://openalex.org/keywords/option-discovery","display_name":"option discovery","score":0.7699999809265137},{"id":"https://openalex.org/keywords/lifelong-reinforcement-learning","display_name":"lifelong reinforcement learning","score":0.984000027179718},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"sample complexity","score":0.9309999942779541},{"id":"https://openalex.org/keywords/pac-analysis","display_name":"PAC analysis","score":0.49799999594688416},{"id":"https://openalex.org/keywords/accelerated-learning","display_name":"accelerated learning","score":0.6399999856948853}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9057513475418091},{"id":"https://openalex.org/C108771440","wikidata":"https://www.wikidata.org/wiki/Q368475","display_name":"Lifelong learning","level":2,"score":0.7845289707183838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7385484576225281},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7291136384010315},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.5915073156356812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5625046491622925},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5189394950866699},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5023617744445801},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0639117956161499},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.668.6194","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.668.6194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://jmlr.org/proceedings/papers/v32/brunskill14.pdf","raw_type":"text"},{"id":"mag:2133458291","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v32/brunskill14.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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W24272225","https://openalex.org/W36691172","https://openalex.org/W107583932","https://openalex.org/W1492014007","https://openalex.org/W1505937442","https://openalex.org/W1517383877","https://openalex.org/W1556824961","https://openalex.org/W1586944634","https://openalex.org/W1592847719","https://openalex.org/W1850488217","https://openalex.org/W1867103660","https://openalex.org/W1991564165","https://openalex.org/W2109910161","https://openalex.org/W2111020392","https://openalex.org/W2114451917","https://openalex.org/W2119567691","https://openalex.org/W2123447947","https://openalex.org/W2142502798","https://openalex.org/W2160808139","https://openalex.org/W2167590754","https://openalex.org/W2169743339","https://openalex.org/W2403765497","https://openalex.org/W2489939061","https://openalex.org/W2964117027"],"related_works":["https://openalex.org/W7097419274","https://openalex.org/W7096808918","https://openalex.org/W7124296148","https://openalex.org/W2396928060","https://openalex.org/W7098188408","https://openalex.org/W2904106049","https://openalex.org/W143164768","https://openalex.org/W1552567658","https://openalex.org/W2498991332","https://openalex.org/W60146956"],"abstract_inverted_index":{"A":[0],"key":[1],"goal":[2],"of":[3,70,76,79,108,114],"AI":[4],"is":[5,34],"to":[6,16,27,45,52],"create":[7],"lifelong":[8,116,137],"learn-ing":[9],"agents":[10],"that":[11,129],"can":[12,48],"leverage":[13],"prior":[14,29,92],"experience":[15,30],"improve":[17],"performance":[18],"on":[19,89,95],"later":[20],"tasks.":[21,60],"In":[22,61],"reinforcement-learning":[23],"problems,":[24],"one":[25],"way":[26],"summarize":[28],"for":[31,43],"future":[32],"use":[33],"through":[35],"options,":[36],"which":[37],"are":[38],"temporally":[39],"extended":[40],"actions":[41],"(subpolicies)":[42],"how":[44,98],"behave.":[46],"Op-tions":[47],"then":[49,104],"be":[50],"used":[51],"potentially":[53],"accelerate":[54,101],"learning":[55,59,77,81,117],"in":[56,110,136],"new":[57,121],"reinforcement":[58,80,138],"this":[62],"work,":[63],"we":[64],"provide":[65],"the":[66,71,106,120],"first":[67],"formal":[68],"analysis":[69,85],"sample":[72,112,134],"complexity,":[73],"a":[74,115,125],"measure":[75],"speed,":[78],"with":[82],"options.":[83],"This":[84],"helps":[86],"shed":[87],"light":[88],"some":[90],"interesting":[91],"empirical":[93],"results":[94],"when":[96],"and":[97],"options":[99,109],"may":[100],"learning.":[102,139],"We":[103],"quantify":[105],"benefit":[107],"reducing":[111],"complexity":[113,135],"agent.":[118],"Finally,":[119],"the-oretical":[122],"insights":[123],"inspire":[124],"novel":[126],"option-discovery":[127],"algorithm":[128],"aims":[130],"at":[131],"minimizing":[132],"overall":[133],"1.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}