{"id":"https://openalex.org/W2099836790","doi":"https://doi.org/10.1109/acc.2008.4587210","title":"Heuristic Dynamic Programming strategy with eligibility traces","display_name":"Heuristic Dynamic Programming strategy with eligibility traces","publication_year":2008,"publication_date":"2008-06-01","ids":{"openalex":"https://openalex.org/W2099836790","doi":"https://doi.org/10.1109/acc.2008.4587210","mag":"2099836790"},"language":"en","primary_location":{"id":"doi:10.1109/acc.2008.4587210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2008.4587210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 American Control Conference","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/A5100455323","display_name":"Tao Li","orcid":"https://orcid.org/0000-0002-6239-969X"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tao Li","raw_affiliation_strings":["Laboratory of Complex Systems and Intelligence Science, Institute of Automation, Chinese Academy and Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Laboratory of Complex Systems and Intelligence Science, Institute of Automation, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["Laboratory of Complex Systems and Intelligence Science, Institute of Automation, Chinese Academy and Sciences, Beijing, China","University of Arizona Tucson, USA"],"affiliations":[{"raw_affiliation_string":"Laboratory of Complex Systems and Intelligence Science, Institute of Automation, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"University of Arizona Tucson, USA","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019541846","display_name":"Jianqiang Yi","orcid":"https://orcid.org/0000-0003-3268-9482"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Yi","raw_affiliation_strings":["Laboratory of Complex Systems and Intelligence Science, Institute of Automation, Chinese Academy and Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Laboratory of Complex Systems and Intelligence Science, Institute of Automation, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100455323"],"corresponding_institution_ids":["https://openalex.org/I4210094879"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.12153727,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4535","last_page":"4540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9986000061035156,"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":0.9323999881744385,"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/heuristics","display_name":"Heuristics","score":0.6679115295410156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6396538019180298},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6233605146408081},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.527404248714447},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5228326916694641},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5129389762878418},{"id":"https://openalex.org/keywords/lambda","display_name":"Lambda","score":0.4970288574695587},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49298784136772156},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4495299756526947},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.44824323058128357},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3985570967197418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35465437173843384},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2595584988594055},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1771361231803894},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14869394898414612}],"concepts":[{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6679115295410156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6396538019180298},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6233605146408081},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.527404248714447},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5228326916694641},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5129389762878418},{"id":"https://openalex.org/C2778113609","wikidata":"https://www.wikidata.org/wiki/Q10897","display_name":"Lambda","level":2,"score":0.4970288574695587},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49298784136772156},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4495299756526947},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.44824323058128357},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3985570967197418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35465437173843384},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2595584988594055},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1771361231803894},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14869394898414612},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acc.2008.4587210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2008.4587210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 American Control Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1574514837","https://openalex.org/W1706571876","https://openalex.org/W1854776945","https://openalex.org/W1995622844","https://openalex.org/W2005189114","https://openalex.org/W2037474012","https://openalex.org/W2105489293","https://openalex.org/W2107726111","https://openalex.org/W2111595076","https://openalex.org/W2114452570","https://openalex.org/W2121863487","https://openalex.org/W2125382903","https://openalex.org/W2126277806","https://openalex.org/W2136064843","https://openalex.org/W2158091072","https://openalex.org/W2160561608","https://openalex.org/W2165501837","https://openalex.org/W2531891978","https://openalex.org/W4302033506","https://openalex.org/W6675733946"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3177062893","https://openalex.org/W3125143773","https://openalex.org/W2007032764","https://openalex.org/W803550684","https://openalex.org/W2483226803","https://openalex.org/W4352977312","https://openalex.org/W2041180560"],"abstract_inverted_index":{"In":[0,54],"traditional":[1],"adaptive":[2],"dynamic":[3,58],"programming":[4,59],"(ADP),":[5],"only":[6],"one":[7],"step":[8],"estimate":[9],"is":[10,18,62,68,78,82,98,125],"considered":[11,107],"for":[12,50,91],"training":[13,143],"process,":[14],"Thus,":[15],"learning":[16,26],"efficiency":[17],"lower.":[19],"If":[20],"more":[21],"steps":[22],"estimates":[23],"are":[24,106],"included,":[25],"process":[27],"will":[28],"be":[29,44],"speed":[30],"up.":[31],"Eligibility":[32],"traces":[33,77],"record":[34],"the":[35],"past":[36],"and":[37,88,104,114,142],"current":[38],"gradients":[39],"of":[40,66,95,111,119],"estimation.":[41],"It":[42],"can":[43],"used":[45],"to":[46,135],"work":[47],"with":[48,75],"ADP":[49,67],"speeding":[51],"up":[52],"learning.":[53],"this":[55],"paper,":[56],"heuristic":[57],"(HDP)":[60],"which":[61],"a":[63,121,128],"typical":[64],"structure":[65],"considered.":[69],"An":[70],"algorithm,":[71],"HDP(lambda),":[72],"integrating":[73],"HDP":[74,103],"eligibility":[76],"presented.":[79],"The":[80,117,130],"algorithm":[81],"illustrated":[83],"from":[84,108],"both":[85,109],"forward":[86],"view":[87,90],"back":[89],"clear":[92],"comprehension.":[93],"Equivalency":[94],"two":[96],"views":[97],"analyzed.":[99],"Furthermore,":[100],"differences":[101],"between":[102],"HDP(lambda)":[105,137],"aspects":[110],"theoretic":[112],"analysis":[113],"simulation":[115],"results.":[116],"problem":[118],"balancing":[120],"pendulum":[122],"robot":[123],"(pendubot)":[124],"adopted":[126],"as":[127],"benchmark.":[129],"results":[131],"indicate":[132],"that":[133],"compared":[134],"HDP,":[136],"shows":[138],"higher":[139],"convergence":[140],"rate":[141],"efficiency.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}