{"id":"https://openalex.org/W3942861","doi":null,"title":"Hierarchical Optimal Control of MDPs","display_name":"Hierarchical Optimal Control of MDPs","publication_year":1998,"publication_date":"1998-01-01","ids":{"openalex":"https://openalex.org/W3942861","mag":"3942861"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.110.5904","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.110.5904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.wustl.edu/~rlg1/rlseminar/papers/mcgovern1998options.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/A5070181594","display_name":"Amy McGovern","orcid":"https://orcid.org/0000-0001-6675-7119","observed_orcids":["https://orcid.org/0000-0001-6675-7119"]},"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":"Amy McGovern","raw_affiliation_strings":["University of Massachusetts: Amherst#TAB#"],"raw_orcid":"https://orcid.org/0000-0001-6675-7119","affiliations":[{"raw_affiliation_string":"University of Massachusetts: Amherst#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065836447","display_name":"Doina Precup","orcid":"https://orcid.org/0000-0003-4718-9851","observed_orcids":["https://orcid.org/0000-0003-4718-9851"]},"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":"Doina Precup","raw_affiliation_strings":["University of Massachusetts: Amherst#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts: Amherst#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009374923","display_name":"Balaraman Ravindran","orcid":"https://orcid.org/0000-0002-5364-7639","observed_orcids":["https://orcid.org/0000-0002-5364-7639"]},"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":"Balaraman Ravindran","raw_affiliation_strings":["University of Massachusetts: Amherst#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-5364-7639","affiliations":[{"raw_affiliation_string":"University of Massachusetts: Amherst#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065366930","display_name":"Satinder Pal Singh","orcid":"https://orcid.org/0000-0002-2736-7641","observed_orcids":["https://orcid.org/0000-0002-2736-7641","https://orcid.org/0000-0002-8215-8295","https://orcid.org/0000-0002-5169-9486","https://orcid.org/0000-0001-9360-7060"]},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Satinder Singh","raw_affiliation_strings":["University of Colorado \u2010 Boulder"],"raw_orcid":"https://orcid.org/0000-0002-5169-9486","affiliations":[{"raw_affiliation_string":"University of Colorado \u2010 Boulder","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023250996","display_name":"Stanley M. Sutton","orcid":null,"observed_orcids":[]},"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":"Stanley M. Sutton","raw_affiliation_strings":["University of Massachusetts: Amherst#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts: Amherst#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113035928","display_name":"Scott F. Richard","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Scott F. Richard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.00052946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10906","display_name":"AI-based Problem Solving and Planning","score":9.999999747378752e-05,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/options-framework","display_name":"options framework","score":0.8769999742507935},{"id":"https://openalex.org/keywords/hierarchical-reinforcement-learning","display_name":"hierarchical reinforcement learning","score":0.8320000171661377},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.9620000123977661},{"id":"https://openalex.org/keywords/semi-markov-decision-process","display_name":"semi-Markov decision process","score":0.9990000128746033},{"id":"https://openalex.org/keywords/temporal-abstraction","display_name":"temporal abstraction","score":0.5929999947547913},{"id":"https://openalex.org/keywords/subtasks","display_name":"subtasks","score":0.5879999995231628},{"id":"https://openalex.org/keywords/termination-conditions","display_name":"termination conditions","score":0.5820000171661377}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8596848249435425},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.8154762983322144},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.678138792514801},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6690162420272827},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5120752453804016},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.47748279571533203},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4595531225204468},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.44548502564430237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4281264543533325},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40377187728881836},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3594186305999756},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11229044198989868},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.110.5904","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.110.5904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.wustl.edu/~rlg1/rlseminar/papers/mcgovern1998options.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.130.4374","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.130.4374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ou.edu/~amy/pubs/options-yale98.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.142.7828","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.142.7828","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/~rich/papers/Yale-98.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.161.6723","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.161.6723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-all.cs.umass.edu/~ravi/papers/mcgovern_prs_YALE98.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.30.7527","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.30.7527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.cs.umass.edu/pub/anw/pub/dprecup/McGovern-Precup-Ravindran-Singh-Sutton-Yale98.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.556.7261","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.556.7261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.eecs.umich.edu/~baveja/Papers/Yale-98.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.9.3670","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.3670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.cs.umass.edu/pub/anw/pub/sutton/Yale-98.ps.gz","raw_type":"text"},{"id":"mag:3942861","doi":null,"is_oa":false,"landing_page_url":"https://web.eecs.umich.edu/~baveja/Papers/Yale-98.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"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":16,"referenced_works":["https://openalex.org/W16046748","https://openalex.org/W1488730473","https://openalex.org/W1494114146","https://openalex.org/W1507087299","https://openalex.org/W1595483645","https://openalex.org/W1600813180","https://openalex.org/W2016482167","https://openalex.org/W2089933214","https://openalex.org/W2102000945","https://openalex.org/W2114451917","https://openalex.org/W2119567691","https://openalex.org/W2153947321","https://openalex.org/W2156067405","https://openalex.org/W2158548602","https://openalex.org/W2160371091","https://openalex.org/W2343637401"],"related_works":["https://openalex.org/W7099597047","https://openalex.org/W2102000945","https://openalex.org/W2109910161","https://openalex.org/W7036529589","https://openalex.org/W2182877511","https://openalex.org/W4399991083","https://openalex.org/W196004314","https://openalex.org/W4393023509","https://openalex.org/W7097419274","https://openalex.org/W1510402218"],"abstract_inverted_index":{"Fundamental":[0],"to":[1,7,46,50,72,163],"reinforcement":[2,142,194],"learning,":[3],"as":[4,6,94],"well":[5],"the":[8,15,21,56,110,134,189],"theory":[9,104],"of":[10,17,27,33,78,90,105,112,130,147,156,177,185,193],"systems":[11],"and":[12,23,55,87,99,114,136,145,159,170,180,191],"control,":[13],"is":[14,81,92,107],"problem":[16],"represent-ing":[18],"knowledge":[19],"about":[20,24],"environment":[22],"possible":[25],"courses":[26],"action":[28,86,91],"hierarchically,":[29],"at":[30,173],"a":[31,39,69,97,100,153,174,182],"multiplicity":[32],"interre-lated":[34],"temporal":[35],"scales.":[36],"For":[37],"example,":[38],"human":[40],"traveler":[41],"must":[42],"decide":[43],"which":[44,76],"cities":[45],"go":[47],"to,":[48],"whether":[49],"fly,":[51],"drive,":[52],"or":[53],"walk,":[54],"individual":[57],"muscle":[58],"contractions":[59],"involved":[60],"in":[61,75,121,128,132,141],"each":[62,77],"step.":[63],"In":[64],"this":[65],"paper":[66],"we":[67],"survey":[68],"new":[70,165],"approach":[71],"reinforce-ment":[73],"learning":[74,171,195],"these":[79,120],"decisions":[80],"treated":[82],"uniformly.":[83],"Each":[84],"low-level":[85],"high-level":[88],"course":[89],"represented":[93],"an":[95],"option,":[96],"(sub)controller":[98],"termination":[101],"condition.":[102],"The":[103],"options":[106,148],"based":[108],"on":[109],"theories":[111],"Markov":[113],"semi-Markov":[115],"decision":[116],"pro-cesses,":[117],"but":[118],"extends":[119],"significant":[122],"ways.":[123],"Options":[124,144,167],"can":[125,149],"be":[126,150],"used":[127,140],"place":[129],"actions":[131],"all":[133],"planning":[135,169],"learn-ing":[137],"methods":[138],"conventionally":[139],"learning.":[143],"models":[146],"learned":[151],"for":[152],"wide":[154,175,183],"variety":[155,176,184],"different":[157],"subtasks,":[158,186],"then":[160],"rapidly":[161],"combined":[162],"solve":[164],"tasks.":[166],"enable":[168],"si-multaneously":[172],"times":[178],"scales,":[179],"toward":[181],"substantially":[187],"increasing":[188],"ef-ficiency":[190],"abilities":[192],"systems.":[196]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}