{"id":"https://openalex.org/W2295413729","doi":"https://doi.org/10.1109/icsmc.2011.6084063","title":"Reinforcement field","display_name":"Reinforcement field","publication_year":2011,"publication_date":"2011-10-01","ids":{"openalex":"https://openalex.org/W2295413729","doi":"https://doi.org/10.1109/icsmc.2011.6084063","mag":"2295413729"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2011.6084063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2011.6084063","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"],"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"]}]},{"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"],"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"]}]}],"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2567","last_page":"2574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9901999831199646,"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":0.9901999831199646,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.97079998254776,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9344000220298767,"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":0.9015774726867676},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.660679042339325},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6185066103935242},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6048861145973206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5522312521934509},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5296143293380737},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4872852563858032},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4812297821044922},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.451654314994812},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4507555365562439},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4475018084049225},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4294856786727905},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41693365573883057},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4109594225883484},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4093739092350006},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.22128859162330627},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21194058656692505},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.20838654041290283},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09625622630119324}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9015774726867676},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.660679042339325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6185066103935242},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6048861145973206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5522312521934509},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5296143293380737},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4872852563858032},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4812297821044922},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.451654314994812},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4507555365562439},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4475018084049225},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4294856786727905},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41693365573883057},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4109594225883484},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4093739092350006},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.22128859162330627},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21194058656692505},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.20838654041290283},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09625622630119324},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2011.6084063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2011.6084063","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":[{"id":"https://metadata.un.org/sdg/16","score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W213343370","https://openalex.org/W1515851193","https://openalex.org/W1560724230","https://openalex.org/W2081766347","https://openalex.org/W2106261932","https://openalex.org/W2143958939","https://openalex.org/W2155234326","https://openalex.org/W2156974606","https://openalex.org/W3144619878","https://openalex.org/W4211049957","https://openalex.org/W6676072908"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W3096874164","https://openalex.org/W4225571923","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W2136202932","https://openalex.org/W2025663273"],"abstract_inverted_index":{"Complex":[0],"control":[1],"tasks":[2],"involving":[3],"varying":[4],"or":[5,66],"evolving":[6],"system":[7],"dynamics":[8],"often":[9,26],"pose":[10],"a":[11,30,42,49,141,157,168,179],"great":[12],"challenge":[13],"to":[14,28,37,48,59,61,96,110,115],"mainstream":[15],"reinforcement":[16,130,138,153],"learning":[17,131,150],"algorithms.":[18],"Specifically,":[19],"in":[20,41,63,68,91,172],"most":[21],"standard":[22,75],"methods,":[23],"actions":[24],"are":[25],"assumed":[27],"be":[29],"concrete":[31],"and":[32,78,105],"fixed":[33],"set":[34],"that":[35],"applies":[36],"the":[38,53,57,69,74,85,88,97,100,108,112,116,120,134,137,148,162],"state":[39,81,103,121,169],"space":[40,104],"predefined":[43],"manner.":[44],"Consequently,":[45],"without":[46],"resorting":[47],"substantial":[50],"re-learning":[51],"procedure,":[52],"derived":[54],"policy":[55,114,149,158],"lacks":[56],"ability":[58],"adapt":[60],"variations":[62],"action":[64,70,76],"outcomes":[65],"shifts":[67],"set.":[71],"In":[72],"addition,":[73],"representation":[77],"its":[79],"attendant":[80],"transition":[82],"mechanism":[83,160],"limit":[84],"applicability":[86],"of":[87,99,107,119,129,136,143,164],"RL":[89],"framework":[90],"complex":[92],"domains":[93],"primarily":[94],"due":[95],"intractability":[98],"resulting":[101],"large":[102],"lack":[106],"facility":[109],"generalize":[111],"learned":[113],"unknown":[117],"parts":[118],"space.":[122],"This":[123],"paper":[124],"proposes":[125],"an":[126],"alternative":[127],"view":[128],"by":[132],"establishing":[133],"notion":[135],"field":[139,154],"through":[140,161],"collection":[142],"policy-embedded":[144],"particles":[145],"gathered":[146],"during":[147],"process.":[151],"The":[152],"serves":[155],"as":[156,167,178],"generalization":[159],"use":[163],"kernel":[165],"functions":[166],"correlation":[170],"hypothesis":[171],"combination":[173],"with":[174],"Gaussian":[175],"process":[176],"regression":[177],"value":[180],"function":[181],"approximator.":[182]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}