{"id":"https://openalex.org/W3089470457","doi":"https://doi.org/10.1109/icarm49381.2020.9195341","title":"Model-Based Reinforcement Learning For Robot Control","display_name":"Model-Based Reinforcement Learning For Robot Control","publication_year":2020,"publication_date":"2020-09-14","ids":{"openalex":"https://openalex.org/W3089470457","doi":"https://doi.org/10.1109/icarm49381.2020.9195341","mag":"3089470457"},"language":"en","primary_location":{"id":"doi:10.1109/icarm49381.2020.9195341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarm49381.2020.9195341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 5th International Conference on Advanced Robotics and Mechatronics (ICARM)","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/A5100658982","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0003-4619-2549"},"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiang Li","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, P. R. China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031221880","display_name":"Weiwei Shang","orcid":"https://orcid.org/0000-0001-7541-2198"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwei Shang","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, P. R. China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047621347","display_name":"Shuang Cong","orcid":"https://orcid.org/0000-0001-8101-0128"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Cong","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, P. R. China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100658982"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.3977,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.69005662,"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":"300","last_page":"305"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9854999780654907,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9850000143051147,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8624477386474609},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7240040302276611},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6453198790550232},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6103854179382324},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.6096110939979553},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5523345470428467},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4843767583370209},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3924955725669861}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8624477386474609},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7240040302276611},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6453198790550232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6103854179382324},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.6096110939979553},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5523345470428467},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4843767583370209},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3924955725669861},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icarm49381.2020.9195341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarm49381.2020.9195341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 5th International Conference on Advanced Robotics and Mechatronics (ICARM)","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":44,"referenced_works":["https://openalex.org/W1520597402","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W1977655452","https://openalex.org/W1980035368","https://openalex.org/W1997543377","https://openalex.org/W2012587148","https://openalex.org/W2121103318","https://openalex.org/W2129202194","https://openalex.org/W2132602063","https://openalex.org/W2140135625","https://openalex.org/W2155007355","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2284050935","https://openalex.org/W2580909119","https://openalex.org/W2785389871","https://openalex.org/W2789824229","https://openalex.org/W2892230114","https://openalex.org/W2901112449","https://openalex.org/W2949571867","https://openalex.org/W2953708620","https://openalex.org/W2962872206","https://openalex.org/W2963238274","https://openalex.org/W2963685250","https://openalex.org/W2963864421","https://openalex.org/W2963960193","https://openalex.org/W2964161785","https://openalex.org/W4205513846","https://openalex.org/W4298206671","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6678367057","https://openalex.org/W6680657880","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6695676441","https://openalex.org/W6730042731","https://openalex.org/W6748519856","https://openalex.org/W6748817170","https://openalex.org/W6751494529","https://openalex.org/W6754471908","https://openalex.org/W6764980988"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W1528400370","https://openalex.org/W2152445738","https://openalex.org/W3038962357"],"abstract_inverted_index":{"Model-free":[0],"deep":[1,122,148],"reinforcement":[2,61],"learning":[3,56,62,77,91],"(MFRL)":[4],"algorithms":[5,68],"have":[6],"achieved":[7],"many":[8],"impressive":[9],"results.":[10],"But":[11],"they":[12],"are":[13,34,69],"generally":[14],"stricken":[15],"with":[16],"high":[17,139],"sample":[18,74],"complexity,":[19],"which":[20],"puts":[21],"forward":[22],"a":[23,52,98,170],"critical":[24],"challenge":[25],"for":[26,36,60,168],"their":[27,102],"application":[28],"to":[29,45,55,63,72,107,125,136,156],"real-world":[30],"robots.":[31],"Dynamic":[32],"models":[33,57],"essential":[35],"robot":[37,158,172],"control":[38,159],"laws,":[39],"but":[40],"it":[41,86,162],"is":[42,97,154],"often":[43],"hard":[44],"obtain":[46],"accurate":[47,93],"analytical":[48],"dynamic":[49,80,95],"models.":[50],"Therefore":[51],"data-driven":[53],"approach":[54],"becomes":[58],"significant":[59],"increase":[64],"data":[65],"efficiency.":[66],"Model-based":[67],"effective":[70],"methods":[71],"reduce":[73],"complexity":[75],"by":[76],"the":[78,108,138,143,147,174],"system":[79,94,127],"model.":[81],"However,":[82],"in":[83,134,173],"certain":[84],"environments,":[85],"has":[87,163],"been":[88,164],"proven":[89],"that":[90],"an":[92,119],"model":[96,131],"formidable":[99],"problem,":[100],"and":[101,129],"asymptotic":[103,140],"performance":[104,141],"cannot":[105],"achieve":[106],"same":[109],"level":[110],"as":[111],"model-free":[112,145],"algorithms.":[113],"In":[114],"our":[115],"work,":[116],"we":[117],"use":[118],"ensemble":[120],"of":[121,142],"neural":[123],"networks":[124],"learn":[126],"dynamics":[128],"incorporate":[130],"uncertainty.":[132],"Then":[133],"order":[135],"merge":[137],"advanced":[144],"methods,":[146],"deterministic":[149],"policy":[150],"gradient":[151],"(DDPG)":[152],"algorithm":[153],"adopted":[155],"optimize":[157],"policy.":[160],"Furthermore,":[161],"implemented":[165],"within":[166],"ROS":[167],"controlling":[169],"Baxter":[171],"simulation":[175],"environment.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}