{"id":"https://openalex.org/W2589147347","doi":"https://doi.org/10.1109/icci-cc.2016.7862056","title":"Enhancing supervisory training signals with environmental reinforcement learning using adaptive dynamic programming and artificial neural networks","display_name":"Enhancing supervisory training signals with environmental reinforcement learning using adaptive dynamic programming and artificial neural networks","publication_year":2016,"publication_date":"2016-08-01","ids":{"openalex":"https://openalex.org/W2589147347","doi":"https://doi.org/10.1109/icci-cc.2016.7862056","mag":"2589147347"},"language":"en","primary_location":{"id":"doi:10.1109/icci-cc.2016.7862056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icci-cc.2016.7862056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","raw_type":"proceedings-article"},"type":"article","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/A5019659003","display_name":"Niklas Melton","orcid":"https://orcid.org/0000-0001-9625-7086"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Niklas Melton","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, Missouri, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, Missouri, USA","institution_ids":["https://openalex.org/I20382870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038037619","display_name":"Donald C. Wunsch","orcid":"https://orcid.org/0000-0002-9726-9051"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donald C. Wunsch","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, Missouri, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, Missouri, USA","institution_ids":["https://openalex.org/I20382870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019659003"],"corresponding_institution_ids":["https://openalex.org/I20382870"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17801047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"331","last_page":"335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955999851226807,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9419999718666077,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8498843908309937},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.753972053527832},{"id":"https://openalex.org/keywords/supervisor","display_name":"Supervisor","score":0.7265928983688354},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6864677667617798},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6504789590835571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6084313988685608},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4650878310203552},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.44327467679977417}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8498843908309937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753972053527832},{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.7265928983688354},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6864677667617798},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6504789590835571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6084313988685608},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4650878310203552},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.44327467679977417},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icci-cc.2016.7862056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icci-cc.2016.7862056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W124618424","https://openalex.org/W1497976081","https://openalex.org/W1622701847","https://openalex.org/W1854776945","https://openalex.org/W1974883306","https://openalex.org/W1994923984","https://openalex.org/W2014081627","https://openalex.org/W2061769196","https://openalex.org/W2091565802","https://openalex.org/W2101761545","https://openalex.org/W2136064843","https://openalex.org/W2166575060","https://openalex.org/W4214717370","https://openalex.org/W4244471710"],"related_works":["https://openalex.org/W4387731985","https://openalex.org/W2755149878","https://openalex.org/W2468425257","https://openalex.org/W2941808082","https://openalex.org/W2528721242","https://openalex.org/W4377009725","https://openalex.org/W4320164562","https://openalex.org/W2356364326","https://openalex.org/W4379086698","https://openalex.org/W2372069567"],"abstract_inverted_index":{"A":[0],"method":[1,47,87],"for":[2],"hybridizing":[3],"supervised":[4],"learning":[5,23,29,41,74],"with":[6],"adaptive":[7],"dynamic":[8],"programming":[9],"was":[10],"developed":[11],"to":[12,32,64],"increase":[13],"the":[14,36,46],"speed,":[15],"quality,":[16],"and":[17,34,50,75,82],"robustness":[18],"of":[19,48],"on-line":[20],"neural":[21],"network":[22],"from":[24],"an":[25],"imperfect":[26],"teacher.":[27],"Reinforcement":[28],"is":[30],"used":[31],"modify":[33],"enhance":[35],"original":[37],"supervisory":[38],"signal":[39],"before":[40],"occurs.":[42],"This":[43],"paper":[44],"describes":[45],"hybridization":[49],"presents":[51],"a":[52,57,61,67],"model":[53],"problem":[54],"in":[55,77],"which":[56],"human":[58],"supervisor":[59],"teaches":[60],"simulated":[62],"car":[63],"drive":[65],"around":[66],"race":[68],"track.":[69],"Simulation":[70],"results":[71],"show":[72],"successful":[73],"improvements":[76],"convergence":[78],"time,":[79],"error":[80],"rate,":[81],"stability":[83],"over":[84],"either":[85],"component":[86],"alone.":[88]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}