{"id":"https://openalex.org/W2139394304","doi":null,"title":"Hierarchical policy gradient algorithms","display_name":"Hierarchical policy gradient algorithms","publication_year":2003,"publication_date":"2003-08-21","ids":{"openalex":"https://openalex.org/W2139394304","mag":"2139394304"},"language":"en","primary_location":{"id":"pmh:oai:scholarworks.umass.edu:cs_faculty_pubs-1182","doi":null,"is_oa":true,"landing_page_url":"https://scholarworks.umass.edu/cs_faculty_pubs/173","pdf_url":"https://scholarworks.umass.edu/cs_faculty_pubs/173","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Department Faculty Publication Series","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://scholarworks.umass.edu/cs_faculty_pubs/173","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013843778","display_name":"Mohammad Ghavamzadeh","orcid":"https://orcid.org/0000-0003-0930-8688","observed_orcids":["https://orcid.org/0000-0003-0930-8688"]},"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":"Mohammad Ghavamzadeh","raw_affiliation_strings":["Department of Computer Science, University of Massachusetts, Amherst, Amherst, MA"],"raw_orcid":"https://orcid.org/0000-0003-0930-8688","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts, Amherst, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061960274","display_name":"Sridhar Mahadevan","orcid":"https://orcid.org/0000-0001-6507-9109","observed_orcids":["https://orcid.org/0000-0001-6507-9109"]},"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":["Department of Computer Science, University of Massachusetts, Amherst, Amherst, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts, Amherst, Amherst, MA","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":1.3907,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.84202821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"226","last_page":"233"},"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/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"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","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/hierarchical-reinforcement-learning","display_name":"hierarchical reinforcement learning","score":0.9900000095367432},{"id":"https://openalex.org/keywords/policy-gradient","display_name":"policy gradient","score":0.7210000157356262},{"id":"https://openalex.org/keywords/continuous-state-action-spaces","display_name":"continuous state and action spaces","score":0.796999990940094},{"id":"https://openalex.org/keywords/hybrid-reinforcement-learning","display_name":"hybrid reinforcement learning","score":0.5879999995231628},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.7749999761581421},{"id":"https://openalex.org/keywords/ship-steering","display_name":"ship steering","score":0.8450000286102295}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9007366299629211},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.707642674446106},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6480607986450195},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6445677280426025},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5631874799728394},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5123566389083862},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.46809911727905273},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4458770751953125},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4422297477722168},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40605786442756653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40596336126327515},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40110623836517334},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22756722569465637},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"pmh:oai:scholarworks.umass.edu:cs_faculty_pubs-1182","doi":null,"is_oa":true,"landing_page_url":"https://scholarworks.umass.edu/cs_faculty_pubs/173","pdf_url":"https://scholarworks.umass.edu/cs_faculty_pubs/173","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Department Faculty Publication Series","raw_type":"text"},{"id":"pmh:oai:works.bepress.com:sridhar_mahadevan-1002","doi":null,"is_oa":true,"landing_page_url":"https://works.bepress.com/sridhar_mahadevan/3","pdf_url":"https://works.bepress.com/sridhar_mahadevan/3","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sridhar Mahadevan","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.117.451","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.117.451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ualberta.ca/~mgh/PUBLICATIONS/icml03.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.329.3993","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.329.3993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aaai.org/Papers/ICML/2003/ICML03-032.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.5.8394","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.5.8394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umass.edu/~mahadeva/./papers/icml03-1.pdf","raw_type":"text"},{"id":"pmh:oai:scholarworks.umass.edu:20.500.14394/9834","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.14394/9834","pdf_url":null,"source":{"id":"https://openalex.org/S4306402057","display_name":"Scholarworks (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"published","raw_type":"Article"},{"id":"mag:2139394304","doi":null,"is_oa":false,"landing_page_url":"https://webdocs.cs.ualberta.ca/~papersdb/uploaded_files/849/paper_icml03.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":{"id":"pmh:oai:scholarworks.umass.edu:cs_faculty_pubs-1182","doi":null,"is_oa":true,"landing_page_url":"https://scholarworks.umass.edu/cs_faculty_pubs/173","pdf_url":"https://scholarworks.umass.edu/cs_faculty_pubs/173","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Department Faculty Publication Series","raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2139394304.pdf","grobid_xml":"https://content.openalex.org/works/W2139394304.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W112321980","https://openalex.org/W135130342","https://openalex.org/W139620917","https://openalex.org/W1488730473","https://openalex.org/W1568042657","https://openalex.org/W2109910161","https://openalex.org/W2144446635","https://openalex.org/W2156737235"],"related_works":["https://openalex.org/W1218520990","https://openalex.org/W7095489022","https://openalex.org/W2382872992","https://openalex.org/W6941289825","https://openalex.org/W2333296430","https://openalex.org/W2613462707","https://openalex.org/W2907385442","https://openalex.org/W256362207","https://openalex.org/W3139474403","https://openalex.org/W2920215304"],"abstract_inverted_index":{"Hierarchical":[0],"reinforcement":[1,22],"learning":[2,12,23],"is":[3],"a":[4,31,56,74,82,116,121],"general":[5],"framework":[6],"which":[7,81],"attempts":[8],"to":[9,33],"accelerate":[10],"policy":[11,20,60],"in":[13,80],"large":[14],"domains.":[15],"On":[16],"the":[17,88,91,102,109],"other":[18],"hand,":[19],"gradient":[21,61],"(PGRL)":[24],"methods":[25],"have":[26],"received":[27],"recent":[28],"attention":[29],"as":[30,95,104],"means":[32],"solve":[34],"problems":[35,64,100],"with":[36,65],"continuous":[37,66,123],"state":[38,67,124],"spaces.":[39,70],"However,":[40],"they":[41],"su#er":[42],"from":[43],"slow":[44],"convergence.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"combine":[50],"these":[51],"two":[52],"approaches":[53],"and":[54,101,120,125],"propose":[55],"family":[57],"of":[58,76,84,90,111],"hierarchical":[59,77],"algorithms":[62,114],"for":[63],"and/or":[68],"action":[69,126],"We":[71,107],"also":[72],"introduce":[73],"class":[75],"hybrid":[78],"algorithms,":[79],"group":[83],"subtasks,":[85],"usually":[86],"at":[87],"higher-levels":[89],"hierarchy,":[92],"are":[93],"formulated":[94],"value":[96],"function-based":[97],"RL":[98],"(VFRL)":[99],"others":[103],"PGRL":[105],"problems.":[106],"demonstrate":[108],"performance":[110],"our":[112],"proposed":[113],"using":[115],"simple":[117],"taxi-fuel":[118],"problem":[119],"complex":[122],"ship":[127],"steering":[128],"domain.":[129]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2016-06-24T00:00:00"}