{"id":"https://openalex.org/W198337890","doi":null,"title":"Hierarchical reinforcement learning with subpolicies specializing for learned subgoals.","display_name":"Hierarchical reinforcement learning with subpolicies specializing for learned subgoals.","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W198337890","mag":"198337890"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.218.3904","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.218.3904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.science.uva.nl/~bram/HRL_NCI.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/A5113647743","display_name":"Bram Bakker","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bram Bakker","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5071172037","display_name":"J\u00fcrgen Schmidhuber","orcid":"https://orcid.org/0000-0002-1468-6758","observed_orcids":["https://orcid.org/0000-0002-1468-6758"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J\u00fcrgen Schmidhuber","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":0.6513,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.7402184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"125","last_page":"130"},"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/T11574","display_name":"Artificial Intelligence in Games","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":1.0},{"id":"https://openalex.org/keywords/subgoal-discovery","display_name":"subgoal discovery","score":0.9089999794960022},{"id":"https://openalex.org/keywords/partial-observability","display_name":"partial observability","score":0.7509999871253967},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.6629999876022339},{"id":"https://openalex.org/keywords/short-term-memory","display_name":"short-term memory","score":0.8370000123977661},{"id":"https://openalex.org/keywords/value-function","display_name":"value function","score":0.5049999952316284},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7480000257492065},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.8930000066757202},{"id":"https://openalex.org/keywords/feedforward-neural-networks","display_name":"feedforward neural networks","score":0.8799999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5252805948257446},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.34991857409477234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3473846912384033},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33144089579582214},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3267533779144287}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.218.3904","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.218.3904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.science.uva.nl/~bram/HRL_NCI.pdf","raw_type":"text"},{"id":"mag:198337890","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/nci/nci2004.html#BakkerS04","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":11,"referenced_works":["https://openalex.org/W1583380718","https://openalex.org/W1592847719","https://openalex.org/W1599347336","https://openalex.org/W1958163169","https://openalex.org/W2107726111","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2126566174","https://openalex.org/W2143435603","https://openalex.org/W2160371091","https://openalex.org/W2548352678"],"related_works":["https://openalex.org/W1578521162","https://openalex.org/W3148270200","https://openalex.org/W7095520200","https://openalex.org/W7099617710","https://openalex.org/W7095687060","https://openalex.org/W7097945031","https://openalex.org/W46670808","https://openalex.org/W7075606714","https://openalex.org/W4221165923","https://openalex.org/W57282082"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,45,59],"method":[4,67],"for":[5,22],"hierarchical":[6,99],"reinforcement":[7,71,100],"learning":[8,72],"in":[9],"which":[10,32],"high-level":[11,91],"policies":[12,18,92],"automatically":[13],"discover":[14],"subgoals,":[15],"and":[16],"low-level":[17,48],"learn":[19],"to":[20,84],"specialize":[21],"different":[23],"subgoals.":[24],"Subgoals":[25],"are":[26],"represented":[27],"as":[28],"desired":[29],"abstract":[30],"observations":[31],"cluster":[33],"raw":[34],"input":[35],"data.":[36],"High-level":[37],"value":[38,49],"functions":[39,50],"cover":[40,51],"the":[41,55],"state":[42,56],"space":[43,57],"at":[44,58],"coarse":[46],"level;":[47],"only":[52],"parts":[53],"of":[54,80],"fine-grained":[60],"level.":[61],"An":[62],"experiment":[63,76],"shows":[64,77],"that":[65],"this":[66],"outperforms":[68],"several":[69],"flat":[70],"methods.":[73],"A":[74],"second":[75],"how":[78],"problems":[79],"partial":[81],"observability":[82],"due":[83],"observation":[85],"abstraction":[86],"can":[87],"be":[88],"overcome":[89],"using":[90],"with":[93],"memory.":[94],"Key":[95],"words":[96],"Reinforcement":[97],"learning,":[98,101],"feedforward":[102],"neural":[103,106],"networks,":[104,107],"recurrent":[105],"MDPs,":[108],"POMDPs,":[109],"short-term":[110],"memory":[111],"1":[112]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}