{"id":"https://openalex.org/W7097757008","doi":null,"title":"1 Hierarchical Abstraction in Reinforcement Learning Based on Feature Discovery","display_name":"1 Hierarchical Abstraction in Reinforcement Learning Based on Feature Discovery","publication_year":2010,"publication_date":"2010-03-13","ids":{"openalex":"https://openalex.org/W7097757008"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.156.4212","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.156.4212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.qub.ac.uk/~B.McCollum/publications/Abstraction%20in%20Reinforcement%20learnng%201.00.pdf","raw_type":"text"},"volume":null,"type":"conference-abstract","is_traditional":false,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhihui Luo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhihui Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"David Bell","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Bell","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110492315","display_name":"Barry McCollum","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barry Mccollum","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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/feature-discovery","display_name":"feature discovery","score":0.9589999914169312},{"id":"https://openalex.org/keywords/semi-markov-decision-process","display_name":"semi-Markov decision process","score":0.9860000014305115},{"id":"https://openalex.org/keywords/task-decomposition","display_name":"task decomposition","score":0.7480000257492065},{"id":"https://openalex.org/keywords/concurrent-learning","display_name":"concurrent learning","score":0.7129999995231628},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"curse of dimensionality","score":0.7710000276565552},{"id":"https://openalex.org/keywords/hierarchical-task-structure","display_name":"hierarchical task structure","score":0.4690000116825104}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8465999960899353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764999866485596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7016000151634216},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.6187999844551086},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5849000215530396},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5508999824523926},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5224999785423279},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45100000500679016},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43959999084472656},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.42969998717308044},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4275999963283539},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.3449000120162964},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.33709999918937683},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.296099990606308},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C123867240","wikidata":"https://www.wikidata.org/wiki/Q3001792","display_name":"Markov blanket","level":5,"score":0.2669000029563904},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.156.4212","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.156.4212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.qub.ac.uk/~B.McCollum/publications/Abstraction%20in%20Reinforcement%20learnng%201.00.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4235743572","https://openalex.org/W7056863049","https://openalex.org/W2306711933","https://openalex.org/W2353325705","https://openalex.org/W1592847719","https://openalex.org/W2296209277","https://openalex.org/W2372300130","https://openalex.org/W3000554410","https://openalex.org/W7223558931","https://openalex.org/W2343320077"],"abstract_inverted_index":{"Abstract":[0],"\u2014":[1],"Hierarchical":[2,227],"reinforcement":[3,155,228],"learning":[4,20,112,119,122,159,172,199,210],"(HRL)":[5],"is":[6,124],"one":[7],"of":[8,17,45,66,74,80,94,97,110,117,197],"the":[9,15,42,46,64,72,78,92,95,115,121,141,146,170,181,198,209,214],"approaches":[10],"taken":[11],"in":[12,19],"dealing":[13],"with":[14,22,105,220],"curse":[16],"dimensionality":[18],"problems":[21],"large":[23],"state":[24,98,189],"and":[25,136,160,191,217],"action":[26,192],"spaces.":[27],"Although":[28],"previous":[29],"work":[30],"on":[31,41,63,77,183,213],"HLR":[32],"has":[33],"shown":[34],"positive":[35],"results,":[36],"there":[37],"exists":[38],"a":[39,55,108,194],"reliance":[40],"predefined":[43],"structure":[44,196],"core":[47],"Markov":[48],"decision":[49,82],"processes":[50,83],"(MDPs).":[51],"This":[52],"paper":[53],"presents":[54],"new":[56,87],"approach":[57],"to":[58,107],"automatically":[59,204],"construct":[60],"HRL":[61,75],"based":[62,76],"discovery":[65],"relevant":[67,157,178],"environmental":[68],"features.":[69],"We":[70,85,134,144],"investigate":[71],"formulation":[73],"theory":[79],"Semi-Markov":[81],"(SMDPs).":[84],"develop":[86],"concurrent":[88,171],"algorithms":[89,148],"that":[90,168],"estimate":[91],"contribution":[93],"combination":[96],"features":[99,179,190],"whose":[100],"relevance":[101],"can":[102,129,175,201,206],"be":[103,130,202],"quantified":[104],"respect":[106],"set":[109],"related":[111,221],"tasks.":[113,185],"Through":[114],"mining":[116],"online":[118],"experience,":[120],"task":[123,162,200,216],"decomposed":[125],"into":[126],"sub-tasks":[127],"which":[128,205],"solved":[131],"as":[132],"SMDPs.":[133],"explain":[135],"demonstrate":[137],"our":[138],"methods":[139],"using":[140,169],"taxi":[142],"domain.":[143],"compare":[145],"proposed":[147],"under":[149],"three":[150],"different":[151],"conditions,":[152],"including":[153],"flat":[154],"learning,":[156],"feature":[158],"hierarchical":[161,195],"learning.":[163],"Our":[164],"validation":[165],"results":[166],"show":[167],"method,":[173],"we":[174],"efficiently":[176],"detect":[177],"from":[180],"environment":[182],"sequential":[184],"Using":[186],"these":[187],"discovered":[188],"features,":[193],"generated":[203],"significantly":[207],"improve":[208],"speed":[211],"both":[212],"current":[215],"other":[218],"tasks":[219],"semantics":[222],"structure.":[223],"Index":[224],"Terms\u2014Feature":[225],"discovery,":[226]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2025-10-27T00:00:00"}