{"id":"https://openalex.org/W2046163713","doi":"https://doi.org/10.1109/icsmc.2011.6084064","title":"Generalized reinforcement learning with concept-driven abstract actions","display_name":"Generalized reinforcement learning with concept-driven abstract actions","publication_year":2011,"publication_date":"2011-10-01","ids":{"openalex":"https://openalex.org/W2046163713","doi":"https://doi.org/10.1109/icsmc.2011.6084064","mag":"2046163713"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2011.6084064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2011.6084064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Systems, Man, and Cybernetics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5003394642","display_name":"Po-Hsiang Chiu","orcid":"https://orcid.org/0000-0001-8816-9799"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Po-Hsiang Chiu","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA","Department of Computer Science and Engineering, University of Texas at Arlington, 76019, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Texas at Arlington, 76019, USA#TAB#","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047174917","display_name":"Manfred Huber","orcid":"https://orcid.org/0009-0007-0294-9147"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manfred Huber","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA","Department of Computer Science and Engineering, University of Texas at Arlington, 76019, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Texas at Arlington, 76019, USA#TAB#","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189196454"],"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":"22","issue":null,"first_page":"2575","last_page":"2582"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9962000250816345,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9962000250816345,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9789000153541565,"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/T14351","display_name":"Statistical and Computational Modeling","score":0.9674999713897705,"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":0.8259638547897339},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7295430898666382},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.607771635055542},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5904752612113953},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5314717888832092},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4954475164413452},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.472332626581192},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47121256589889526},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4440366327762604},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4412882924079895},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4185875952243805},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41405779123306274},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.13109278678894043},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12764647603034973}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8259638547897339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7295430898666382},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.607771635055542},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5904752612113953},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5314717888832092},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4954475164413452},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.472332626581192},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47121256589889526},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4440366327762604},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4412882924079895},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4185875952243805},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41405779123306274},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.13109278678894043},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12764647603034973},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2011.6084064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2011.6084064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Systems, Man, and Cybernetics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1510073064","https://openalex.org/W1515851193","https://openalex.org/W2121947440","https://openalex.org/W2142505627","https://openalex.org/W2143958939","https://openalex.org/W2160808139","https://openalex.org/W2166618252","https://openalex.org/W2295413729","https://openalex.org/W3103882218","https://openalex.org/W4211049957","https://openalex.org/W4292156489","https://openalex.org/W6677945368","https://openalex.org/W6785592962"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2743976221"],"abstract_inverted_index":{"The":[0,113],"standard":[1,85],"reinforcement":[2,95],"learning":[3,40,86,96],"framework":[4,93],"often":[5,30,81],"faces":[6],"challenges":[7],"in":[8,19,46,56,75],"a":[9,34,68,82,91,145,151,163],"varying":[10],"or":[11,60],"evolving":[12],"environment":[13],"due":[14],"to":[15,32,38,51,53,67,101,149],"an":[16,103],"inherent":[17],"limitation":[18],"its":[20],"representation.":[21],"In":[22,72],"particular,":[23],"useful":[24],"actions":[25,123,157],"for":[26,84],"decision":[27,110,130],"making":[28],"are":[29,142],"assumed":[31],"be":[33],"prefixed":[35],"set":[36,63,152],"prior":[37],"the":[39,43,49,57,61,76,99,109,121,127,133,160],"process.":[41,71],"Consequently,":[42],"derived":[44],"policy":[45,111],"general":[47],"lacks":[48],"ability":[50],"adapt":[52],"possible":[54],"variations":[55],"action":[58,62],"outcomes":[59],"itself":[64],"without":[65],"resorting":[66],"substantial":[69],"re-learning":[70],"addition,":[73],"complexity":[74],"state":[77],"space":[78],"modeling":[79],"is":[80],"bottleneck":[83],"methods.":[87],"This":[88],"paper":[89],"proposes":[90],"new":[92,114],"of":[94,153],"that":[97],"enables":[98],"agent":[100,161],"formulate":[102],"action-oriented":[104],"conceptual":[105],"model":[106],"while":[107],"deriving":[108],"simultaneously.":[112],"framework,":[115],"Concept-Driven":[116],"Learning":[117],"Architecture":[118],"(CDLA),":[119],"formulates":[120],"abstract":[122,156],"based":[124],"on":[125],"associating":[126],"correlated":[128],"past":[129],"history.":[131],"Specifically,":[132],"kernel":[134],"function,":[135],"Gaussian":[136],"process":[137],"and":[138],"spectral":[139],"clustering":[140,147],"mechanisms":[141],"combined":[143],"into":[144],"functional":[146],"method":[148],"identify":[150],"coherent,":[154],"concept-driven":[155],"using":[158],"which":[159],"derives":[162],"control":[164],"policy.":[165]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}