{"id":"https://openalex.org/W112321980","doi":null,"title":"Hierarchically Optimal Average Reward Reinforcement Learning","display_name":"Hierarchically Optimal Average Reward Reinforcement Learning","publication_year":2002,"publication_date":"2002-07-08","ids":{"openalex":"https://openalex.org/W112321980","mag":"112321980"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.16.5072","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.16.5072","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/ho-avg-rl.ps.gz","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/A5013843778","display_name":"Mohammad Ghavamzadeh","orcid":"https://orcid.org/0000-0003-0930-8688","observed_orcids":["https://orcid.org/0000-0003-0930-8688"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad Ghavamzadeh","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0930-8688","affiliations":[]},{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sridhar Mahadevan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3655,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.88568544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"195","last_page":"202"},"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":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/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/hierarchical-reinforcement-learning","display_name":"hierarchical reinforcement learning","score":0.9980000257492065},{"id":"https://openalex.org/keywords/average-reward","display_name":"average reward","score":0.8330000042915344},{"id":"https://openalex.org/keywords/task-hierarchy","display_name":"task hierarchy","score":0.7110000252723694},{"id":"https://openalex.org/keywords/optimal-policy","display_name":"optimal policy","score":0.6970000267028809},{"id":"https://openalex.org/keywords/reinforcement-learning-algorithms","display_name":"reinforcement learning algorithms","score":0.5950000286102295}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8078097105026245},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6745479106903076},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4686640501022339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41677114367485046},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16492891311645508},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10870641469955444}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.16.5072","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.16.5072","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/ho-avg-rl.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.17.7483","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.17.7483","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/icml02.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.93.6195","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.93.6195","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/icml02.pdf","raw_type":"text"},{"id":"mag:112321980","doi":null,"is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/conf/icml/icml2002.html#GhavamzadehM02","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W139620917","https://openalex.org/W165707239","https://openalex.org/W1549353711","https://openalex.org/W1568042657","https://openalex.org/W1597309614","https://openalex.org/W2089561656","https://openalex.org/W2095770075","https://openalex.org/W2101915445","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2153947321","https://openalex.org/W2154204727","https://openalex.org/W2334782222"],"related_works":["https://openalex.org/W7096132658","https://openalex.org/W2143496582","https://openalex.org/W1936091723","https://openalex.org/W7097243042","https://openalex.org/W1218520990","https://openalex.org/W325315585","https://openalex.org/W256362207","https://openalex.org/W2185078385","https://openalex.org/W7142575183","https://openalex.org/W7075606714"],"abstract_inverted_index":{"Two":[0],"notions":[1],"of":[2,127],"optimality":[3],"have":[4,140],"been":[5],"explored":[6],"in":[7,21,108],"previous":[8,113,146],"work":[9,114],"on":[10,82],"hierarchical":[11,15,156],"reinforcement":[12],"learning":[13],"(HRL):":[14],"optimality,":[16],"or":[17],"the":[18,22,105,136,145,153],"optimal":[19,50,63,148,157],"policy":[20],"space":[23],"defined":[24],"by":[25,90],"a":[26,30,66,71,83,120,128],"task":[27],"hierarchy,":[28],"and":[29,70,92,111],"weaker":[31],"local":[32],"model":[33],"called":[34],"recursive":[35],"optimality.":[36],"In":[37],"this":[38,109],"paper,":[39],"we":[40],"introduce":[41],"two":[42],"new":[43,78,137],"average-reward":[44,138],"HRL":[45],"algorithms":[46,59,79,106,139],"for":[47,60,130],"finding":[48],"hierarchically":[49],"policies.":[51],"We":[52],"compare":[53],"them":[54],"to":[55],"our":[56,112],"previously":[57],"reported":[58],"computing":[61],"recursively":[62,147],"policies,":[64],"using":[65],"grid-world":[67],"taxi":[68],"problem":[69],"more":[72],"real-world":[73],"AGV":[74],"scheduling":[75],"problem.":[76],"The":[77],"are":[80],"based":[81],"three-part":[84],"value":[85,98],"function":[86,99],"decomposition":[87],"proposed":[88,107],"recently":[89],"Andre":[91],"Russell,":[93],"which":[94],"generalizes":[95],"Dietterich\u2019s":[96],"MAXQ":[97],"decomposition.":[100],"A":[101],"key":[102],"difference":[103],"between":[104],"paper":[110],"is":[115,118],"that":[116],"there":[117],"only":[119],"single":[121],"global":[122],"gain":[123,129],"(average":[124],"reward),":[125],"instead":[126],"each":[131],"subtask.":[132],"Our":[133],"results":[134],"show":[135],"better":[141],"performance":[142],"than":[143],"both":[144],"counterparts,":[149],"as":[150,152],"well":[151],"corresponding":[154],"discounted":[155],"algorithms.":[158],"1.":[159]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2016-06-24T00:00:00"}