{"id":"https://openalex.org/W4249441547","doi":"https://doi.org/10.1023/a:1025696116075","title":"Recent Advances in Hierarchical Reinforcement Learning","display_name":"Recent Advances in Hierarchical Reinforcement Learning","publication_year":2003,"publication_date":"2003-09-23","ids":{"openalex":"https://openalex.org/W4249441547","doi":"https://doi.org/10.1023/a:1025696116075"},"language":"en","primary_location":{"id":"doi:10.1023/a:1025696116075","is_oa":false,"landing_page_url":"https://doi.org/10.1023/a:1025696116075","pdf_url":null,"source":{"id":"https://openalex.org/S134484881","display_name":"Discrete Event Dynamic Systems","issn_l":"0924-6703","issn":["0924-6703","1573-7594"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discrete Event Dynamic Systems","raw_type":"journal-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/A5089808068","display_name":"Andrew G. Barto","orcid":null},"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":["Autonomous Learning Laboratory, Department of Computer Science, University of Massachusetts, Amherst, MA, 01003"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Learning Laboratory, Department of Computer Science, University of Massachusetts, Amherst, MA, 01003","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061960274","display_name":"Sridhar Mahadevan","orcid":null},"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":"Sridhar Mahadevan","raw_affiliation_strings":["Autonomous Learning Laboratory, Department of Computer Science, University of Massachusetts, Amherst, MA, 01003"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Learning Laboratory, Department of Computer Science, University of Massachusetts, Amherst, MA, 01003","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":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":3.8693,"has_fulltext":false,"cited_by_count":309,"citation_normalized_percentile":{"value":0.93975239,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"13","issue":"4","first_page":"341","last_page":"379"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7903000116348267,"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":0.7903000116348267,"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/observability","display_name":"Observability","score":0.840773344039917},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.7851992249488831},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7542511224746704},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.7042578458786011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6992311477661133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5646349191665649},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5545498728752136},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4388049244880676},{"id":"https://openalex.org/keywords/curse","display_name":"Curse","score":0.43670111894607544},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36946970224380493},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3272339701652527},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10939830541610718},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.08850663900375366}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.840773344039917},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.7851992249488831},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7542511224746704},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.7042578458786011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6992311477661133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5646349191665649},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5545498728752136},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4388049244880676},{"id":"https://openalex.org/C2780273121","wikidata":"https://www.wikidata.org/wiki/Q109411","display_name":"Curse","level":2,"score":0.43670111894607544},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36946970224380493},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3272339701652527},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10939830541610718},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.08850663900375366},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1023/a:1025696116075","is_oa":false,"landing_page_url":"https://doi.org/10.1023/a:1025696116075","pdf_url":null,"source":{"id":"https://openalex.org/S134484881","display_name":"Discrete Event Dynamic Systems","issn_l":"0924-6703","issn":["0924-6703","1573-7594"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discrete Event Dynamic Systems","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-160208","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-160208","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W16046748","https://openalex.org/W34013550","https://openalex.org/W112321980","https://openalex.org/W139620917","https://openalex.org/W142462678","https://openalex.org/W189950281","https://openalex.org/W198956113","https://openalex.org/W1503515926","https://openalex.org/W1515224583","https://openalex.org/W1526807135","https://openalex.org/W1545148916","https://openalex.org/W1549353711","https://openalex.org/W1556565860","https://openalex.org/W1564534945","https://openalex.org/W1568042657","https://openalex.org/W1574700590","https://openalex.org/W1575388622","https://openalex.org/W1598052524","https://openalex.org/W1600813180","https://openalex.org/W1607896167","https://openalex.org/W1636244751","https://openalex.org/W1839010533","https://openalex.org/W1969166509","https://openalex.org/W1982678075","https://openalex.org/W1991622981","https://openalex.org/W2001729196","https://openalex.org/W2009533501","https://openalex.org/W2016482167","https://openalex.org/W2020149918","https://openalex.org/W2020294948","https://openalex.org/W2035032881","https://openalex.org/W2040598998","https://openalex.org/W2041367235","https://openalex.org/W2067352298","https://openalex.org/W2075754841","https://openalex.org/W2088956500","https://openalex.org/W2098589862","https://openalex.org/W2099529102","https://openalex.org/W2107726111","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2123952007","https://openalex.org/W2131466408","https://openalex.org/W2139418546","https://openalex.org/W2143435603","https://openalex.org/W2150339816","https://openalex.org/W2152185829","https://openalex.org/W2155791599","https://openalex.org/W2155872498","https://openalex.org/W2161608691","https://openalex.org/W2165131254","https://openalex.org/W2168359464","https://openalex.org/W2334782222","https://openalex.org/W3183630977","https://openalex.org/W3213472335","https://openalex.org/W4213303927","https://openalex.org/W4229739354","https://openalex.org/W4250835088","https://openalex.org/W4252939763","https://openalex.org/W6634528131","https://openalex.org/W6676772908","https://openalex.org/W6681672201","https://openalex.org/W6683443546","https://openalex.org/W6684037837"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2967463586","https://openalex.org/W2765830098","https://openalex.org/W1971989957","https://openalex.org/W2561617217","https://openalex.org/W3080676530","https://openalex.org/W3158353707","https://openalex.org/W3088621770","https://openalex.org/W4287662386","https://openalex.org/W2115449043"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":20},{"year":2025,"cited_by_count":44},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":18},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":18},{"year":2013,"cited_by_count":20},{"year":2012,"cited_by_count":23}],"updated_date":"2026-08-12T07:12:00.856984","created_date":"2022-05-12T00:00:00"}
