{"id":"https://openalex.org/W4205831613","doi":"https://doi.org/10.1007/s10489-021-02953-8","title":"Offline reinforcement learning with anderson acceleration for robotic tasks","display_name":"Offline reinforcement learning with anderson acceleration for robotic tasks","publication_year":2022,"publication_date":"2022-01-10","ids":{"openalex":"https://openalex.org/W4205831613","doi":"https://doi.org/10.1007/s10489-021-02953-8"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-021-02953-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-021-02953-8","pdf_url":null,"source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-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/A5017790030","display_name":"Guoyu Zuo","orcid":"https://orcid.org/0000-0002-7624-4728"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoyu Zuo","raw_affiliation_strings":["Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, 100124, China","Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, 100124, China","institution_ids":[]},{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101542272","display_name":"Shuai Huang","orcid":"https://orcid.org/0000-0002-4344-5064"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Huang","raw_affiliation_strings":["Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, 100124, China","Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, 100124, China","institution_ids":[]},{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069607848","display_name":"Jiangeng Li","orcid":"https://orcid.org/0000-0001-5715-7824"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiangeng Li","raw_affiliation_strings":["Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, 100124, China","Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China"],"raw_orcid":"https://orcid.org/0000-0001-5715-7824","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, 100124, China","institution_ids":[]},{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010150668","display_name":"Daoxiong Gong","orcid":"https://orcid.org/0000-0003-2492-9159"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daoxiong Gong","raw_affiliation_strings":["Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, 100124, China","Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, 100124, China","institution_ids":[]},{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5069607848"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":0.232,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57169295,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"52","issue":"9","first_page":"9885","last_page":"9898"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9979000091552734,"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":0.9979000091552734,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9919999837875366,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9708999991416931,"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":0.9211243987083435},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8639389276504517},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.7106784582138062},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5633702278137207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.555921196937561},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.5344585180282593},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49748852849006653},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4715423882007599},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.45212414860725403},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.44438156485557556},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43903839588165283},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.43689560890197754},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4363996684551239},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.18608695268630981},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12193763256072998}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9211243987083435},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8639389276504517},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.7106784582138062},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5633702278137207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.555921196937561},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.5344585180282593},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49748852849006653},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4715423882007599},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.45212414860725403},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44438156485557556},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43903839588165283},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.43689560890197754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4363996684551239},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.18608695268630981},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12193763256072998},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10489-021-02953-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-021-02953-8","pdf_url":null,"source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1527702126","https://openalex.org/W1547105496","https://openalex.org/W2251955814","https://openalex.org/W2788862220","https://openalex.org/W2921015455","https://openalex.org/W2963044034","https://openalex.org/W2963099939","https://openalex.org/W2978612180","https://openalex.org/W3080232699","https://openalex.org/W3094477866","https://openalex.org/W3121045039","https://openalex.org/W3121342653","https://openalex.org/W3166492115","https://openalex.org/W4206434057","https://openalex.org/W4245296547","https://openalex.org/W6600902652","https://openalex.org/W6601211009","https://openalex.org/W6603732165","https://openalex.org/W6824051750"],"related_works":["https://openalex.org/W4226283576","https://openalex.org/W4319083788","https://openalex.org/W3022038857","https://openalex.org/W2973438361","https://openalex.org/W4318621078","https://openalex.org/W3099159407","https://openalex.org/W4287063340","https://openalex.org/W3156313910","https://openalex.org/W3191556308","https://openalex.org/W4311991951"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}