{"id":"https://openalex.org/W2970398105","doi":"https://doi.org/10.1109/icinfa.2018.8812454","title":"Research on Online Reinforcement Learning Method Based on Experience-Replay","display_name":"Research on Online Reinforcement Learning Method Based on Experience-Replay","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2970398105","doi":"https://doi.org/10.1109/icinfa.2018.8812454","mag":"2970398105"},"language":"en","primary_location":{"id":"doi:10.1109/icinfa.2018.8812454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icinfa.2018.8812454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Information and Automation (ICIA)","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/A5100783980","display_name":"Ning Hu","orcid":"https://orcid.org/0000-0002-6444-8467"},"institutions":[{"id":"https://openalex.org/I4210113818","display_name":"China Electronic Product Reliability and Environmental Test Institute","ror":"https://ror.org/01f4k3b46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210113818"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ning Hu","raw_affiliation_strings":["China Electronic Product Reliability and Environmental Testing Research Institute, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"China Electronic Product Reliability and Environmental Testing Research Institute, Guangzhou, China","institution_ids":["https://openalex.org/I4210113818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100295999","display_name":"Zhijun Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113818","display_name":"China Electronic Product Reliability and Environmental Test Institute","ror":"https://ror.org/01f4k3b46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210113818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijun Ge","raw_affiliation_strings":["China Electronic Product Reliability and Environmental Testing Research Institute, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"China Electronic Product Reliability and Environmental Testing Research Institute, Guangzhou, China","institution_ids":["https://openalex.org/I4210113818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049930758","display_name":"Xuanwen Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113818","display_name":"China Electronic Product Reliability and Environmental Test Institute","ror":"https://ror.org/01f4k3b46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210113818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanwen Chen","raw_affiliation_strings":["China Electronic Product Reliability and Environmental Testing Research Institute, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"China Electronic Product Reliability and Environmental Testing Research Institute, Guangzhou, China","institution_ids":["https://openalex.org/I4210113818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074031902","display_name":"Chunguang Ding","orcid":"https://orcid.org/0000-0001-9051-7297"},"institutions":[{"id":"https://openalex.org/I4210113818","display_name":"China Electronic Product Reliability and Environmental Test Institute","ror":"https://ror.org/01f4k3b46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210113818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunguang Ding","raw_affiliation_strings":["China Electronic Product Reliability and Environmental Testing Research Institute, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"China Electronic Product Reliability and Environmental Testing Research Institute, Guangzhou, China","institution_ids":["https://openalex.org/I4210113818"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013665827","display_name":"Haobin Shi","orcid":"https://orcid.org/0000-0003-2180-8941"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haobin Shi","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100783980"],"corresponding_institution_ids":["https://openalex.org/I4210113818"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24249327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"1338","last_page":"1343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9926999807357788,"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/T14413","display_name":"Advanced Technologies in Various Fields","score":0.9258000254631042,"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":0.8274314403533936},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7525237202644348},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.43780261278152466},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4286551773548126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.413251668214798},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33709102869033813}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8274314403533936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7525237202644348},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43780261278152466},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4286551773548126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.413251668214798},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33709102869033813}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icinfa.2018.8812454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icinfa.2018.8812454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Information and Automation (ICIA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W560518094","https://openalex.org/W1589747210","https://openalex.org/W1600437712","https://openalex.org/W1977655452","https://openalex.org/W2050238052","https://openalex.org/W2052688942","https://openalex.org/W2100677568","https://openalex.org/W2146502635","https://openalex.org/W2165726932","https://openalex.org/W2195446438","https://openalex.org/W2266260776","https://openalex.org/W2331984051","https://openalex.org/W2766447205","https://openalex.org/W3041202696","https://openalex.org/W3139377883","https://openalex.org/W4253978526"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"As":[0],"for":[1,39,60],"standard":[2],"reinforcement":[3,41,97,114],"learning,":[4],"the":[5,9,16,25,35,44,52,61,70,75,85,93,101,111,118,126,129],"key":[6],"is":[7,13,58],"that":[8],"agent\u2019s":[10],"next":[11],"step":[12],"directed":[14],"by":[15,99,116],"instantaneous":[17],"and":[18,27,29,77,108],"delayed":[19],"reporting":[20],"from":[21],"constant":[22],"interaction":[23],"with":[24],"environment":[26],"trial":[28],"error":[30],"learning.":[31],"But":[32],"it":[33,57],"makes":[34],"convergence":[36,76,94],"rate":[37,95],"slower":[38],"actual":[40],"learning;":[42],"at":[43],"same":[45],"time,":[46],"inconsistency":[47],"state":[48],"will":[49],"occur":[50],"in":[51],"agent":[53,62],"learning":[54,98,115],"process.":[55],"Therefore,":[56],"necessary":[59],"to":[63,73,84,91,109],"remember":[64],"what":[65],"has":[66],"been":[67],"learned":[68],"within":[69],"time":[71],"specified":[72],"improve":[74,110],"robustness":[78,112],"of":[79,96,105,113,128],"decision":[80],"making.":[81],"With":[82],"regard":[83],"above-mentioned":[86],"issues,":[87],"this":[88],"paper":[89],"proposes":[90],"accelerate":[92],"using":[100,117],"function":[102],"approximation":[103],"ability":[104],"neural":[106],"network":[107],"Memory-based":[119],"Experience-Replay(ER)":[120],"algorithm.":[121],"The":[122],"experimental":[123],"results":[124],"show":[125],"effectiveness":[127],"proposed":[130],"method.":[131]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}