{"id":"https://openalex.org/W16046748","doi":null,"title":"Reinforcement learning with a hierarchy of abstract models","display_name":"Reinforcement learning with a hierarchy of abstract models","publication_year":1992,"publication_date":"1992-07-12","ids":{"openalex":"https://openalex.org/W16046748","mag":"16046748"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.32.8362","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.32.8362","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/singh/singh-AAAI92.ps.Z","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/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/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":true,"raw_author_name":"Satinder Singh","raw_affiliation_strings":["Dept of Computer Science, University of Massachusetts, Amherst, MA"],"raw_orcid":"https://orcid.org/0000-0002-2736-7641","affiliations":[{"raw_affiliation_string":"Dept of Computer Science, University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5065366930"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":3.5012,"has_fulltext":false,"cited_by_count":108,"citation_normalized_percentile":{"value":0.92349267,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"202","last_page":"207"},"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/T12072","display_name":"Machine Learning and Algorithms","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/reinforcement-learning","display_name":"reinforcement learning","score":0.9240000247955322},{"id":"https://openalex.org/keywords/hierarchical-models","display_name":"hierarchical models","score":0.5899999737739563},{"id":"https://openalex.org/keywords/simulated-experience","display_name":"simulated experience","score":0.6209999918937683},{"id":"https://openalex.org/keywords/environmental-models","display_name":"environmental models","score":0.5379999876022339},{"id":"https://openalex.org/keywords/hierarchical-planning","display_name":"hierarchical planning","score":0.734000027179718},{"id":"https://openalex.org/keywords/lookahead-planning","display_name":"lookahead planning","score":0.656000018119812},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.7039999961853027},{"id":"https://openalex.org/keywords/temporal-abstraction","display_name":"temporal abstraction","score":0.5889999866485596}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8687140345573425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8163295984268188},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.808448076248169},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6758397817611694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.589253842830658},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5627170205116272},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4248344302177429},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4213051199913025},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08695346117019653},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.32.8362","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.32.8362","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/singh/singh-AAAI92.ps.Z","raw_type":"text"},{"id":"mag:16046748","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/aaai/aaai92.html#Singh92","pdf_url":null,"source":{"id":"https://openalex.org/S4306420577","display_name":"National Conference on Artificial Intelligence","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":"National Conference on Artificial Intelligence","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":16,"referenced_works":["https://openalex.org/W50425026","https://openalex.org/W1491843047","https://openalex.org/W1503515926","https://openalex.org/W1526807135","https://openalex.org/W1555519929","https://openalex.org/W1586172133","https://openalex.org/W1586504939","https://openalex.org/W1595634327","https://openalex.org/W1610678877","https://openalex.org/W1640646391","https://openalex.org/W1931792391","https://openalex.org/W2001729196","https://openalex.org/W2012036715","https://openalex.org/W2100677568","https://openalex.org/W2103626435","https://openalex.org/W2166996723"],"related_works":["https://openalex.org/W2394068835","https://openalex.org/W1526807135","https://openalex.org/W7075606714","https://openalex.org/W7124166887","https://openalex.org/W2293201763","https://openalex.org/W4298683466","https://openalex.org/W1936091723","https://openalex.org/W7100775682","https://openalex.org/W57282082","https://openalex.org/W7095489022"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,13,65],"(RL)":[2],"algorithms":[3,32],"have":[4],"traditionally":[5],"been":[6],"thought":[7],"of":[8,68,70,80,84,106],"as":[9,35,77],"trial":[10],"and":[11,44],"error":[12],"methods":[14],"that":[15,30,45,73,98],"use":[16],"actual":[17],"control":[18,24],"experience":[19,39,124],"to":[20,51,94,101],"incrementally":[21],"improve":[22],"a":[23,66,78,104],"policy.":[25],"Sutton's":[26,95],"DYNA":[27,96],"architecture":[28,97],"demonstrated":[29],"RL":[31,85],"can":[33],"work":[34],"well":[36],"using":[37,123],"simulated":[38],"from":[40,111],"an":[41,92],"environment":[42,72],"model,":[43],"the":[46,58,71,82,118],"resulting":[47],"computation":[48],"was":[49],"similar":[50],"doing":[52],"one-step":[53],"lookahead":[54],"planning.":[55],"Inspired":[56],"by":[57],"literature":[59],"on":[60],"hierarchical":[61,112],"planning,":[62],"I":[63,87],"propose":[64],"hierarchy":[67,105],"models":[69,120],"abstract":[74,107,119],"temporal":[75],"detail":[76],"means":[79],"improving":[81],"scalability":[83],"algorithms.":[86],"present":[88],"H-DYNA":[89,109],"(Hierarchical":[90],"DYNA),":[91],"extension":[93],"is":[99],"able":[100],"learn":[102],"such":[103],"models.":[108],"differs":[110],"planners":[113],"in":[114],"two":[115],"ways:":[116],"first,":[117],"are":[121],"learned":[122],"gained":[125],"while...":[126]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}