{"id":"https://openalex.org/W3139474403","doi":"https://doi.org/10.5555/1314498.1390329","title":"Hierarchical Average Reward Reinforcement Learning","display_name":"Hierarchical Average Reward Reinforcement Learning","publication_year":2007,"publication_date":"2007-12-01","ids":{"openalex":"https://openalex.org/W3139474403","doi":"https://doi.org/10.5555/1314498.1390329","mag":"3139474403"},"language":"en","primary_location":{"id":"mag:3139474403","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.5555/1314498.1390329","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research","raw_type":null},"type":"article","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/A5079532673","display_name":"GhavamzadehMohammad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"GhavamzadehMohammad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5085811250","display_name":"MahadevanSridhar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"MahadevanSridhar","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":1.1767,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87070106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"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/T11729","display_name":"Product Development and Customization","score":0.14920000731945038,"subfield":{"id":"https://openalex.org/subfields/1405","display_name":"Management of Technology and Innovation"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11729","display_name":"Product Development and Customization","score":0.14920000731945038,"subfield":{"id":"https://openalex.org/subfields/1405","display_name":"Management of Technology and Innovation"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.1274999976158142,"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/T12659","display_name":"Innovation Diffusion and Forecasting","score":0.1251000016927719,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.731236457824707},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6246377229690552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49124854803085327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47968244552612305},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.43149927258491516},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3635791540145874},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3015759587287903},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.11844509840011597}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.731236457824707},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6246377229690552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49124854803085327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47968244552612305},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.43149927258491516},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3635791540145874},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3015759587287903},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.11844509840011597}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3139474403","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.5555/1314498.1390329","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Journal of Machine Learning Research","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1936091723","https://openalex.org/W2185078385","https://openalex.org/W1508965793","https://openalex.org/W3101152497","https://openalex.org/W2349158267","https://openalex.org/W1713467276","https://openalex.org/W2775148797","https://openalex.org/W139620917","https://openalex.org/W2963182798","https://openalex.org/W3029383961","https://openalex.org/W3092312937","https://openalex.org/W2920654375","https://openalex.org/W2779282916","https://openalex.org/W1492974543","https://openalex.org/W2353741066","https://openalex.org/W3013076952","https://openalex.org/W1530955640","https://openalex.org/W2673096016","https://openalex.org/W3092207185","https://openalex.org/W3045465479"],"abstract_inverted_index":{"Hierarchical":[0],"reinforcement":[1,10],"learning":[2,11],"(HRL)":[3],"is":[4],"a":[5],"general":[6],"framework":[7],"for":[8],"scaling":[9],"(RL)":[12],"to":[13,28],"problems":[14],"with":[15],"large":[16],"state":[17],"and":[18],"action":[19],"spaces":[20],"by":[21],"using":[22],"the":[23],"task":[24],"(or":[25],"action)":[26],"structure":[27],"re...":[29]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-10-10T17:16:08.811792","created_date":"2025-10-10T00:00:00"}