{"id":"https://openalex.org/W4386883595","doi":"https://doi.org/10.1109/rcar58764.2023.10250060","title":"Reinforcement Learning with Goal Relabeling and Dynamic Model for Robotic Tasks","display_name":"Reinforcement Learning with Goal Relabeling and Dynamic Model for Robotic Tasks","publication_year":2023,"publication_date":"2023-07-17","ids":{"openalex":"https://openalex.org/W4386883595","doi":"https://doi.org/10.1109/rcar58764.2023.10250060"},"language":"en","primary_location":{"id":"doi:10.1109/rcar58764.2023.10250060","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/rcar58764.2023.10250060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Real-time Computing and Robotics (RCAR)","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/A5101958555","display_name":"Kun Dong","orcid":"https://orcid.org/0000-0002-5440-185X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kun Dong","raw_affiliation_strings":["Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China","HFIPS, Chinese Academy of Sciences, Institute of Intelligent Machines, Hefei, China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences, Institute of Intelligent Machines, Hefei, China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058229499","display_name":"Yongle Luo","orcid":"https://orcid.org/0000-0001-9933-3611"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongle Luo","raw_affiliation_strings":["Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China","University of Science and Technology of China, Hefei, China","HFIPS, Chinese Academy of Sciences, Institute of Intelligent Machines, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences, Institute of Intelligent Machines, Hefei, China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427490","display_name":"Yuxin Wang","orcid":"https://orcid.org/0009-0004-4110-3513"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Wang","raw_affiliation_strings":["Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China","HFIPS, Chinese Academy of Sciences, Institute of Intelligent Machines, Hefei, China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences, Institute of Intelligent Machines, Hefei, China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001772658","display_name":"Shan Fang","orcid":"https://orcid.org/0000-0002-8742-8557"},"institutions":[{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]},{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Fang","raw_affiliation_strings":["Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China","University of Science and Technology of China, Hefei, China","HFIPS, Chinese Academy of Sciences, Institute of Intelligent Machines, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences, Institute of Intelligent Machines, Hefei, China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100736937","display_name":"Yu Liu","orcid":"https://orcid.org/0009-0002-0821-5316"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]},{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China","HFIPS, Chinese Academy of Sciences, Institute of Intelligent Machines, Hefei, China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences, Institute of Intelligent Machines, Hefei, China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059137735","display_name":"Erkang Cheng","orcid":"https://orcid.org/0000-0001-7941-6911"},"institutions":[{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]},{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Erkang Cheng","raw_affiliation_strings":["Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China","HFIPS, Chinese Academy of Sciences, Institute of Intelligent Machines, Hefei, China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences, Institute of Intelligent Machines, Hefei, China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727179","display_name":"Zhiyong Sun","orcid":"https://orcid.org/0000-0001-9510-4897"},"institutions":[{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Sun","raw_affiliation_strings":["Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China","HFIPS, Chinese Academy of Sciences, Institute of Intelligent Machines, Hefei, China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences, Institute of Intelligent Machines, Hefei, China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381999","display_name":"Qiang Zhang","orcid":"https://orcid.org/0000-0003-3776-9799"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Zhang","raw_affiliation_strings":["Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China","HFIPS, Chinese Academy of Sciences, Institute of Intelligent Machines, Hefei, China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences, Institute of Intelligent Machines, Hefei, China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060524697","display_name":"Bo Song","orcid":"https://orcid.org/0000-0003-2307-8524"},"institutions":[{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]},{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Song","raw_affiliation_strings":["Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China","HFIPS, Chinese Academy of Sciences, Institute of Intelligent Machines, Hefei, China","University of Science and Technology of China, Hefei, China","Jianghuai Frontier Technology Coordination and Innovation Center, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Institute of Intelligent Machines,HFIPS, Chinese Academy of Sciences,Hefei,China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"HFIPS, Chinese Academy of Sciences, Institute of Intelligent Machines, Hefei, China","institution_ids":["https://openalex.org/I4210099079","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Jianghuai Frontier Technology Coordination and Innovation Center, Hefei, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101958555"],"corresponding_institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210099079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11638348,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"847","last_page":"852"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9679999947547913,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.960099995136261,"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":0.8612828254699707},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8332067728042603},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5350052118301392},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5064493417739868},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5015711784362793},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48373866081237793},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45659008622169495},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4402180314064026},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.42354580760002136}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8612828254699707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8332067728042603},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5350052118301392},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5064493417739868},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5015711784362793},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48373866081237793},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45659008622169495},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4402180314064026},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.42354580760002136},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rcar58764.2023.10250060","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/rcar58764.2023.10250060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Real-time Computing and Robotics (RCAR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1980035368","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2580909119","https://openalex.org/W2781726626","https://openalex.org/W2810754397","https://openalex.org/W2859967432","https://openalex.org/W2902907165","https://openalex.org/W2950564923","https://openalex.org/W2953708620","https://openalex.org/W3034680299","https://openalex.org/W3038822267","https://openalex.org/W3086270667","https://openalex.org/W3092490845","https://openalex.org/W3123636359","https://openalex.org/W3135642434","https://openalex.org/W3173254652","https://openalex.org/W3192510920","https://openalex.org/W4288319859","https://openalex.org/W4298206671","https://openalex.org/W4298857966","https://openalex.org/W4299806248","https://openalex.org/W4300799055","https://openalex.org/W6637967152","https://openalex.org/W6680657880","https://openalex.org/W6740801417","https://openalex.org/W6747473740","https://openalex.org/W6750253780","https://openalex.org/W6751494529","https://openalex.org/W6753183898","https://openalex.org/W6753264383","https://openalex.org/W6763990646","https://openalex.org/W6764053384","https://openalex.org/W6764980988","https://openalex.org/W6779142360","https://openalex.org/W6783909840","https://openalex.org/W6789172296","https://openalex.org/W6797745118","https://openalex.org/W6802051021"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175"],"abstract_inverted_index":{"Improving":[0],"sample":[1,20,189],"efficiency":[2,21,190],"is":[3,51,60,165],"crucial":[4],"for":[5,9],"reinforcement":[6,101,150],"learning,":[7],"especially":[8],"the":[10,19,36,41,48,54,57,66,69,73,78,88,91,113,115,118,125,139,155,159,162,172,180,183],"robot":[11],"manipulation":[12],"tasks.":[13],"The":[14,142],"model-based":[15,177],"method":[16,103,144,164,185],"could":[17],"improve":[18],"by":[22,53,72,124,131],"introducing":[23,132],"a":[24,29,83,99,133,149,187],"dynamic":[25,49,109,134,200],"model":[26,50,58,135],"to":[27,82,136],"generate":[28],"large":[30],"number":[31],"of":[32,38,68,90,117,161,171,196],"samples,":[33],"so":[34],"that":[35,158,169],"requirement":[37],"interaction":[39],"with":[40],"environment":[42],"can":[43],"be":[44,122],"reduced.":[45],"However,":[46],"as":[47],"constructed":[52],"deep":[55],"network,":[56],"error":[59,63],"inevitable.":[61],"This":[62],"will":[64,121],"increase":[65,138],"errors":[67],"data":[70,93,120,140],"generated":[71],"model,":[74],"which":[75],"may":[76],"damage":[77],"policy":[79],"training":[80],"process":[81],"certain":[84],"extent.":[85],"To":[86],"overcome":[87],"limitations":[89],"above":[92],"augmentation":[94],"methods,":[95],"this":[96],"paper":[97],"proposes":[98],"new":[100],"learning":[102,151],"based":[104],"on":[105],"goal":[106,126,173,197],"relabeling":[107,127,174,198],"and":[108,154,175,199],"(GMRL)":[110],"model.":[111,201],"In":[112],"GMRL,":[114],"quality":[116],"explored":[119],"improved":[123],"at":[128],"first,":[129],"followed":[130],"further":[137],"quantity.":[141],"proposed":[143,163,184],"has":[145,186],"been":[146],"tested":[147],"in":[148],"benchmark":[152],"environment,":[153],"results":[156],"show":[157],"performance":[160],"significantly":[166],"better":[167],"than":[168,191],"both":[170],"standard":[176],"methods.":[178],"At":[179],"same":[181],"time,":[182],"higher":[188],"other":[192],"existing":[193],"combined":[194],"schema":[195]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}
