{"id":"https://openalex.org/W1988688219","doi":"https://doi.org/10.1109/tnnls.2013.2271454","title":"Goal Representation Heuristic Dynamic Programming on Maze Navigation","display_name":"Goal Representation Heuristic Dynamic Programming on Maze Navigation","publication_year":2013,"publication_date":"2013-07-22","ids":{"openalex":"https://openalex.org/W1988688219","doi":"https://doi.org/10.1109/tnnls.2013.2271454","mag":"1988688219","pmid":"https://pubmed.ncbi.nlm.nih.gov/24805221"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2013.2271454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2013.2271454","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://digitalcommons.uri.edu/ele_facpubs/554","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075006150","display_name":"Zhen Ni","orcid":"https://orcid.org/0000-0003-3166-4726"},"institutions":[{"id":"https://openalex.org/I17626003","display_name":"University of Rhode Island","ror":"https://ror.org/013ckk937","country_code":"US","type":"education","lineage":["https://openalex.org/I17626003"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhen Ni","raw_affiliation_strings":["Department of Electrical, Computer and Biomedical Engineering, University of Rhode Island, Kingston, RI, USA","Dept of Electr., Comput., & Biomed. Eng., Univ. of Rhode Island, Kingston, RI, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer and Biomedical Engineering, University of Rhode Island, Kingston, RI, USA","institution_ids":["https://openalex.org/I17626003"]},{"raw_affiliation_string":"Dept of Electr., Comput., & Biomed. Eng., Univ. of Rhode Island, Kingston, RI, USA","institution_ids":["https://openalex.org/I17626003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110390415","display_name":"Haibo He","orcid":null},"institutions":[{"id":"https://openalex.org/I17626003","display_name":"University of Rhode Island","ror":"https://ror.org/013ckk937","country_code":"US","type":"education","lineage":["https://openalex.org/I17626003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haibo He","raw_affiliation_strings":["Department of Electrical, Computer and Biomedical Engineering, University of Rhode Island, Kingston, RI, USA","Dept of Electr., Comput., & Biomed. Eng., Univ. of Rhode Island, Kingston, RI, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer and Biomedical Engineering, University of Rhode Island, Kingston, RI, USA","institution_ids":["https://openalex.org/I17626003"]},{"raw_affiliation_string":"Dept of Electr., Comput., & Biomed. Eng., Univ. of Rhode Island, Kingston, RI, USA","institution_ids":["https://openalex.org/I17626003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641767","display_name":"Jinyu Wen","orcid":"https://orcid.org/0000-0002-0288-727X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyu Wen","raw_affiliation_strings":["Huazhong University of Science and Technology, School of Electrical and Electronic Engineering, Wuhan, China","Coll. of Mechatron. & Autom., Nat. Univ. of Defense Tech, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, School of Electrical and Electronic Engineering, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Coll. of Mechatron. & Autom., Nat. Univ. of Defense Tech, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["National University of Defense Technology, College of Mechatronics and Automation, Changsha, China","State Key Lab. of Adv. Electromagn. Eng. & Technol., Huazhong Univ. of Sci. & Technol., Wuhan, , China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, College of Mechatronics and Automation, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"State Key Lab. of Adv. Electromagn. Eng. & Technol., Huazhong Univ. of Sci. & Technol., Wuhan, , China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5075006150"],"corresponding_institution_ids":["https://openalex.org/I17626003"],"apc_list":null,"apc_paid":null,"fwci":16.4148,"has_fulltext":false,"cited_by_count":106,"citation_normalized_percentile":{"value":0.99409323,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"24","issue":"12","first_page":"2038","last_page":"2050"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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":0.8345736265182495},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7443121671676636},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7168214321136475},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6868481636047363},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6427384614944458},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6127184629440308},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6046079993247986},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5919471383094788},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5690557956695557},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5414677858352661},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4998602867126465},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49369463324546814},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.4492340683937073},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34440964460372925},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.34352022409439087},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19581112265586853},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11586618423461914}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8345736265182495},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7443121671676636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7168214321136475},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6868481636047363},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6427384614944458},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6127184629440308},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6046079993247986},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5919471383094788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5690557956695557},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5414677858352661},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4998602867126465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49369463324546814},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4492340683937073},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34440964460372925},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.34352022409439087},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19581112265586853},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11586618423461914},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2013.2271454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2013.2271454","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:24805221","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24805221","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:digitalcommons.uri.edu:ele_facpubs-1553","is_oa":true,"landing_page_url":"https://digitalcommons.uri.edu/ele_facpubs/554","pdf_url":null,"source":{"id":"https://openalex.org/S2764761010","display_name":"Journal of Media Literacy Education","issn_l":"2167-8715","issn":["2167-8715"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310316378","host_organization_name":"National Association for Media Literacy Education","host_organization_lineage":["https://openalex.org/P4310316378"],"host_organization_lineage_names":["National Association for Media Literacy Education"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical, Computer, and Biomedical Engineering Faculty Publications","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:digitalcommons.uri.edu:ele_facpubs-1553","is_oa":true,"landing_page_url":"https://digitalcommons.uri.edu/ele_facpubs/554","pdf_url":null,"source":{"id":"https://openalex.org/S2764761010","display_name":"Journal of Media Literacy Education","issn_l":"2167-8715","issn":["2167-8715"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310316378","host_organization_name":"National Association for Media Literacy Education","host_organization_lineage":["https://openalex.org/P4310316378"],"host_organization_lineage_names":["National Association for Media Literacy Education"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical, Computer, and Biomedical Engineering Faculty Publications","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W42269961","https://openalex.org/W560518094","https://openalex.org/W603852980","https://openalex.org/W1491843047","https://openalex.org/W1569296262","https://openalex.org/W1570487003","https://openalex.org/W1824921430","https://openalex.org/W1841450225","https://openalex.org/W1965227651","https://openalex.org/W1966517492","https://openalex.org/W1982710301","https://openalex.org/W1983089547","https://openalex.org/W1987204351","https://openalex.org/W1994616650","https://openalex.org/W1994849207","https://openalex.org/W2005675298","https://openalex.org/W2007640554","https://openalex.org/W2033326237","https://openalex.org/W2060605484","https://openalex.org/W2089762101","https://openalex.org/W2098432798","https://openalex.org/W2100677568","https://openalex.org/W2105004188","https://openalex.org/W2105922750","https://openalex.org/W2107674817","https://openalex.org/W2111980775","https://openalex.org/W2115249980","https://openalex.org/W2116488102","https://openalex.org/W2120624705","https://openalex.org/W2120924101","https://openalex.org/W2121863487","https://openalex.org/W2123491406","https://openalex.org/W2124829859","https://openalex.org/W2132858840","https://openalex.org/W2136064843","https://openalex.org/W2149009003","https://openalex.org/W2149398074","https://openalex.org/W2152445738","https://openalex.org/W2158091072","https://openalex.org/W2165501837","https://openalex.org/W2341171179","https://openalex.org/W2484646121","https://openalex.org/W2531891978","https://openalex.org/W2541582879","https://openalex.org/W3041202696","https://openalex.org/W4214717370","https://openalex.org/W4238986444","https://openalex.org/W4248400504","https://openalex.org/W4302033506","https://openalex.org/W6638759419","https://openalex.org/W6678423249","https://openalex.org/W6682178038"],"related_works":["https://openalex.org/W2903299703","https://openalex.org/W4281791088","https://openalex.org/W4385342861","https://openalex.org/W4308702637","https://openalex.org/W1574958246","https://openalex.org/W2808418668","https://openalex.org/W61119710","https://openalex.org/W4256087190","https://openalex.org/W4240668504","https://openalex.org/W2011233848"],"abstract_inverted_index":{"Goal":[0],"representation":[1,35],"heuristic":[2,51],"dynamic":[3,52],"programming":[4,53],"(GrHDP)":[5],"is":[6,105],"proposed":[7,41,76,109,146],"in":[8,15,27,50,137,158,161],"this":[9],"paper":[10],"to":[11,22,60,66,94,139],"demonstrate":[12,140],"online":[13],"learning":[14,100,118,124],"the":[16,23,37,40,47,62,69,95,99,103,117,131,141,150,154],"Markov":[17],"decision":[18],"process.":[19],"In":[20,112],"addition":[21],"(external)":[24],"reinforcement":[25,123],"signal":[26],"literature,":[28],"we":[29,45,114,148],"develop":[30],"an":[31],"adaptively":[32],"internal":[33,63],"goal/reward":[34],"for":[36,134],"agent":[38,104],"with":[39,107,120],"goal":[42,58,64],"network.":[43],"Specifically,":[44],"keep":[46],"actor-critic":[48],"design":[49],"(HDP)":[54],"and":[55,85,128],"include":[56,116],"a":[57],"network":[59],"represent":[61],"signal,":[65],"further":[67],"help":[68],"value":[70],"function":[71],"approximation.":[72],"We":[73],"evaluate":[74],"our":[75,108,145,162],"GrHDP":[77,110,163],"algorithm":[78],"on":[79,87,130],"two":[80,121],"2-D":[81],"maze":[82,90],"navigation":[83,91],"problems,":[84],"later":[86],"one":[88],"3-D":[89],"problem.":[92],"Compared":[93],"traditional":[96],"HDP":[97],"approach,":[98],"performance":[101,119],"of":[102,144,156],"improved":[106],"approach.":[111,164],"addition,":[113],"also":[115],"other":[122],"algorithms,":[125],"namely":[126],"Sarsa(\u03bb)":[127],"Q-learning,":[129],"same":[132],"benchmarks":[133],"comparison.":[135],"Furthermore,":[136],"order":[138],"theoretical":[142],"guarantee":[143],"method,":[147],"provide":[149],"characteristics":[151],"analysis":[152],"toward":[153],"convergence":[155],"weights":[157],"neural":[159],"networks":[160]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":17},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}