{"id":"https://openalex.org/W4392861284","doi":"https://doi.org/10.3389/fnbot.2024.1368243","title":"Human skill knowledge guided global trajectory policy reinforcement learning method","display_name":"Human skill knowledge guided global trajectory policy reinforcement learning method","publication_year":2024,"publication_date":"2024-03-15","ids":{"openalex":"https://openalex.org/W4392861284","doi":"https://doi.org/10.3389/fnbot.2024.1368243","pmid":"https://pubmed.ncbi.nlm.nih.gov/38559491"},"language":"en","primary_location":{"id":"doi:10.3389/fnbot.2024.1368243","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2024.1368243","pdf_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2024.1368243/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2024.1368243/pdf?isPublishedV2=False","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029687405","display_name":"Yajing Zang","orcid":"https://orcid.org/0000-0003-3353-7894"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yajing Zang","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","State Key Laboratory of Robotics and System, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399559","display_name":"Pengfei Wang","orcid":"https://orcid.org/0000-0002-4218-5467"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Wang","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","State Key Laboratory of Robotics and System, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008850130","display_name":"Fusheng Zha","orcid":"https://orcid.org/0000-0001-9695-1940"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fusheng Zha","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","State Key Laboratory of Robotics and System, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103673923","display_name":"Wei Guo","orcid":"https://orcid.org/0009-0006-5319-5691"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Guo","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","State Key Laboratory of Robotics and System, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003558867","display_name":"Chuan-Feng Li","orcid":"https://orcid.org/0000-0003-4328-3517"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanfeng Li","raw_affiliation_strings":["School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, China","School of Electronics and Information Engineering, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Electronics and Information Engineering, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114160714","display_name":"Lining Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lining Sun","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","State Key Laboratory of Robotics and System, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5029687405"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":{"value":2950,"currency":"USD","value_usd":2950},"apc_paid":{"value":2950,"currency":"USD","value_usd":2950},"fwci":1.0135,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7431524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"18","issue":null,"first_page":"1368243","last_page":"1368243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996399998664856,"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/T10982","display_name":"Motor Control and Adaptation","score":0.9531999826431274,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8377655744552612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8188232183456421},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.7986468076705933},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.637722909450531},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5728427171707153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5686315298080444},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4639444351196289},{"id":"https://openalex.org/keywords/trajectory-optimization","display_name":"Trajectory optimization","score":0.4518047869205475},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.4371151924133301}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8377655744552612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8188232183456421},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7986468076705933},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.637722909450531},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5728427171707153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5686315298080444},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4639444351196289},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.4518047869205475},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4371151924133301},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fnbot.2024.1368243","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2024.1368243","pdf_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2024.1368243/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},{"id":"pmid:38559491","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38559491","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":"Frontiers in neurorobotics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10978794","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10978794","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10978794/pdf/fnbot-18-1368243.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Neurorobot","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:426e9012ab8a40c4a2c4ea3cca4214c5","is_oa":true,"landing_page_url":"https://doaj.org/article/426e9012ab8a40c4a2c4ea3cca4214c5","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Neurorobotics, Vol 18 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fnbot.2024.1368243","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2024.1368243","pdf_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2024.1368243/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1522862786","display_name":null,"funder_award_id":"1521003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1912309979","display_name":null,"funder_award_id":"61911530250","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2482890223","display_name":null,"funder_award_id":"51521003","funder_id":"https://openalex.org/F4320327001","funder_display_name":"State Key Laboratory of Robotics and System"},{"id":"https://openalex.org/G2981938667","display_name":null,"funder_award_id":"Shenzhen","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3757194791","display_name":null,"funder_award_id":"JCYJ20","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4667037360","display_name":null,"funder_award_id":"202060","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G478387158","display_name":null,"funder_award_id":"U2013602","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5383534787","display_name":null,"funder_award_id":"51521003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5700546074","display_name":null,"funder_award_id":"SKLRS202110B","funder_id":"https://openalex.org/F4320327001","funder_display_name":"State Key Laboratory of Robotics and System"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7539905487","display_name":null,"funder_award_id":"202110","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7724035697","display_name":null,"funder_award_id":"SKLRS202001B","funder_id":"https://openalex.org/F4320327001","funder_display_name":"State Key Laboratory of Robotics and System"},{"id":"https://openalex.org/G8383839868","display_name":null,"funder_award_id":"U201360","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8992481365","display_name":null,"funder_award_id":"52075115","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326907","display_name":"State Key Laboratory of Robotics","ror":null},{"id":"https://openalex.org/F4320327001","display_name":"State Key Laboratory of Robotics and System","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392861284.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1574928409","https://openalex.org/W2103831616","https://openalex.org/W2137375617","https://openalex.org/W2171302338","https://openalex.org/W2466175722","https://openalex.org/W2883899184","https://openalex.org/W2906613229","https://openalex.org/W2944455043","https://openalex.org/W2958441538","https://openalex.org/W2967060478","https://openalex.org/W2967322066","https://openalex.org/W2975243818","https://openalex.org/W3001711609","https://openalex.org/W3033312324","https://openalex.org/W3034819467","https://openalex.org/W3081877091","https://openalex.org/W3128463899","https://openalex.org/W3130634520","https://openalex.org/W3155877522","https://openalex.org/W3175584021","https://openalex.org/W3192484395","https://openalex.org/W4205788769","https://openalex.org/W4283365039","https://openalex.org/W4285294350","https://openalex.org/W4291653325","https://openalex.org/W4296425656","https://openalex.org/W4312625742","https://openalex.org/W4313131480","https://openalex.org/W4313368693","https://openalex.org/W4315648377","https://openalex.org/W4321607911","https://openalex.org/W4361205690","https://openalex.org/W4365421136","https://openalex.org/W4367663367","https://openalex.org/W4377971355","https://openalex.org/W4381550403","https://openalex.org/W4385626951","https://openalex.org/W4388635713","https://openalex.org/W4389371347","https://openalex.org/W6680322746","https://openalex.org/W6716193690"],"related_works":["https://openalex.org/W2903025760","https://openalex.org/W4289147272","https://openalex.org/W4385832323","https://openalex.org/W4244391535","https://openalex.org/W2356996864","https://openalex.org/W2904060783","https://openalex.org/W2015393961","https://openalex.org/W2378339670","https://openalex.org/W2359353485","https://openalex.org/W2139910871"],"abstract_inverted_index":{"Traditional":[0],"trajectory":[1,13,26,47,76,100,186],"learning":[2,48],"methods":[3],"based":[4],"on":[5],"Imitation":[6],"Learning":[7,55],"(IL)":[8],"only":[9],"learn":[10,118],"the":[11,25,29,35,39,59,63,81,93,103,107,112,119,123,130,142,146,152,162,170,173,191,194,212,216],"existing":[12],"knowledge":[14,27,60,104],"from":[15],"human":[16],"demonstration.":[17],"In":[18,67],"this":[19,43,68],"way,":[20],"it":[21],"can":[22],"not":[23,138],"adapt":[24,58],"to":[28,57,62,73,92,116,128,140,169,180],"task":[30,114,164],"environment":[31,36,64,95,202],"by":[32,96],"interacting":[33],"with":[34,53],"and":[37,78,85,106,125,145,159,166,183,190],"fine-tuning":[38],"policy.":[40,187],"To":[41],"address":[42],"problem,":[44],"a":[45,199,204],"global":[46,185],"method":[49,195],"which":[50,89],"combinines":[51],"IL":[52,70],"Reinforcement":[54],"(RL)":[56],"policy":[61,88,105,144,214],"is":[65,71,90],"proposed.":[66],"paper,":[69],"proposed":[72],"acquire":[74],"basic":[75,99],"skills,":[77],"then":[79,167],"learns":[80],"agent":[82],"will":[83],"explore":[84],"exploit":[86],"more":[87],"applicable":[91],"current":[94],"RL.":[97],"The":[98,188],"skills":[101],"include":[102],"time":[108,120],"stage":[109],"information":[110],"in":[111,161,198,215],"whole":[113,163],"space":[115,165],"help":[117],"series":[121],"of":[122,149,193,203],"trajectory,":[124],"are":[126,137,157],"used":[127,139],"guide":[129],"subsequent":[131],"RL":[132,150,153,174],"process.":[133,154],"Notably,":[134],"neural":[135],"networks":[136,171],"model":[141],"action":[143],"Q":[147],"value":[148],"during":[151],"Instead,":[155],"they":[156],"sampled":[158],"updated":[160],"transferred":[168],"after":[172],"process":[175],"through":[176],"Behavior":[177],"Cloning":[178],"(BC)":[179],"get":[181],"continuous":[182],"smooth":[184],"feasibility":[189],"effectiveness":[192],"was":[196],"validated":[197],"custom":[200],"Gym":[201],"flower":[205],"drawing":[206,219],"task.":[207],"And":[208],"then,":[209],"we":[210],"executed":[211],"learned":[213],"real-world":[217],"robot":[218],"experiment.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}