{"id":"https://openalex.org/W4313898607","doi":"https://doi.org/10.3390/s23020762","title":"Variational Information Bottleneck Regularized Deep Reinforcement Learning for Efficient Robotic Skill Adaptation","display_name":"Variational Information Bottleneck Regularized Deep Reinforcement Learning for Efficient Robotic Skill Adaptation","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4313898607","doi":"https://doi.org/10.3390/s23020762","pmid":"https://pubmed.ncbi.nlm.nih.gov/36679561"},"language":"en","primary_location":{"id":"doi:10.3390/s23020762","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23020762","pdf_url":"https://www.mdpi.com/1424-8220/23/2/762/pdf?version=1673331769","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/23/2/762/pdf?version=1673331769","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031150449","display_name":"Guofei Xiang","orcid":"https://orcid.org/0000-0003-4934-4237"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210145005","display_name":"State Key Laboratory of Vehicle NVH and Safety Technology","ror":"https://ror.org/04e6h1p91","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145005"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guofei Xiang","raw_affiliation_strings":["College of Electrical Engineering, Sichuan University, Chengdu 610065, China","National Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology, Baotou 014031, China"],"raw_orcid":"https://orcid.org/0000-0003-4934-4237","affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Sichuan University, Chengdu 610065, China","institution_ids":["https://openalex.org/I24185976"]},{"raw_affiliation_string":"National Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology, Baotou 014031, China","institution_ids":["https://openalex.org/I4210145005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028285183","display_name":"Songyi Dian","orcid":"https://orcid.org/0000-0002-4093-3839"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songyi Dian","raw_affiliation_strings":["College of Electrical Engineering, Sichuan University, Chengdu 610065, China"],"raw_orcid":"https://orcid.org/0000-0002-4093-3839","affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Sichuan University, Chengdu 610065, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069810673","display_name":"Shaofeng Du","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145005","display_name":"State Key Laboratory of Vehicle NVH and Safety Technology","ror":"https://ror.org/04e6h1p91","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145005"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shaofeng Du","raw_affiliation_strings":["National Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology, Baotou 014031, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology, Baotou 014031, China","institution_ids":["https://openalex.org/I4210145005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083132239","display_name":"Zhonghui Lv","orcid":"https://orcid.org/0000-0001-5186-3699"},"institutions":[{"id":"https://openalex.org/I4210145005","display_name":"State Key Laboratory of Vehicle NVH and Safety Technology","ror":"https://ror.org/04e6h1p91","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145005"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhonghui Lv","raw_affiliation_strings":["National Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology, Baotou 014031, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology, Baotou 014031, China","institution_ids":["https://openalex.org/I4210145005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069810673"],"corresponding_institution_ids":["https://openalex.org/I4210145005"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":0.6479,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73163572,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"23","issue":"2","first_page":"762","last_page":"762"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9947999715805054,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.8774384260177612},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8288545608520508},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6462807655334473},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6286625862121582},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5620194673538208},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5466159582138062},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.5067272782325745},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4423108994960785},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4273131787776947},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15204304456710815},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.08989444375038147}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8774384260177612},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8288545608520508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6462807655334473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6286625862121582},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5620194673538208},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5466159582138062},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.5067272782325745},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4423108994960785},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4273131787776947},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15204304456710815},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.08989444375038147},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000064","descriptor_name":"Acclimatization","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000064","descriptor_name":"Acclimatization","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000064","descriptor_name":"Acclimatization","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008124","descriptor_name":"Locomotion","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008124","descriptor_name":"Locomotion","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008124","descriptor_name":"Locomotion","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D065287","descriptor_name":"Robotic Surgical Procedures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D065287","descriptor_name":"Robotic Surgical Procedures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D065287","descriptor_name":"Robotic Surgical Procedures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.3390/s23020762","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23020762","pdf_url":"https://www.mdpi.com/1424-8220/23/2/762/pdf?version=1673331769","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:36679561","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36679561","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":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9864208","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9864208","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC9864208/pdf/sensors-23-00762.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:aa0e3356f4574a6c82ece32014285bdc","is_oa":true,"landing_page_url":"https://doaj.org/article/aa0e3356f4574a6c82ece32014285bdc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 23, Iss 2, p 762 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/23/2/762/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s23020762","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Sensors; Volume 23; Issue 2; Pages: 762","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s23020762","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23020762","pdf_url":"https://www.mdpi.com/1424-8220/23/2/762/pdf?version=1673331769","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G3231043308","display_name":null,"funder_award_id":"2023NSFSC1441","funder_id":"https://openalex.org/F4320329861","funder_display_name":"Natural Science Foundation of Sichuan Province"},{"id":"https://openalex.org/G4112234785","display_name":null,"funder_award_id":"2023NSFSC0475","funder_id":"https://openalex.org/F4320329861","funder_display_name":"Natural Science Foundation of Sichuan Province"},{"id":"https://openalex.org/G5556225345","display_name":null,"funder_award_id":"2022SCU12004","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320329861","display_name":"Natural Science Foundation of Sichuan Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4313898607.pdf"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W23576351","https://openalex.org/W91593682","https://openalex.org/W282757658","https://openalex.org/W1513084430","https://openalex.org/W1977655452","https://openalex.org/W2012587148","https://openalex.org/W2027600769","https://openalex.org/W2056518977","https://openalex.org/W2069361969","https://openalex.org/W2109910161","https://openalex.org/W2117539524","https://openalex.org/W2137825550","https://openalex.org/W2145339207","https://openalex.org/W2145962650","https://openalex.org/W2158782408","https://openalex.org/W2165698076","https://openalex.org/W2257979135","https://openalex.org/W2260756217","https://openalex.org/W2281096776","https://openalex.org/W2335959470","https://openalex.org/W2342662072","https://openalex.org/W2411690432","https://openalex.org/W2427497464","https://openalex.org/W2472819217","https://openalex.org/W2593044849","https://openalex.org/W2594103415","https://openalex.org/W2604763608","https://openalex.org/W2754517384","https://openalex.org/W2755546070","https://openalex.org/W2781726626","https://openalex.org/W2788904251","https://openalex.org/W2901112449","https://openalex.org/W2910273746","https://openalex.org/W2910474428","https://openalex.org/W2911087563","https://openalex.org/W2912399346","https://openalex.org/W2914949695","https://openalex.org/W2919115771","https://openalex.org/W2954737642","https://openalex.org/W2962887844","https://openalex.org/W2963026768","https://openalex.org/W2963244934","https://openalex.org/W2981344907","https://openalex.org/W2981762858","https://openalex.org/W2996320484","https://openalex.org/W3005451807","https://openalex.org/W3109467707","https://openalex.org/W3121342653","https://openalex.org/W3200650887","https://openalex.org/W4205430897","https://openalex.org/W4221160818","https://openalex.org/W6638018090","https://openalex.org/W6653548176","https://openalex.org/W6717697761","https://openalex.org/W6751869817"],"related_works":["https://openalex.org/W1504394672","https://openalex.org/W2622284819","https://openalex.org/W3089381707","https://openalex.org/W3034190530","https://openalex.org/W2741297526","https://openalex.org/W4295728955","https://openalex.org/W3129794609","https://openalex.org/W2949033103","https://openalex.org/W2304083841","https://openalex.org/W2362448732"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"(DRL)":[3],"algorithms":[4],"have":[5],"been":[6,17,94,116],"widely":[7],"studied":[8],"for":[9,102],"sequential":[10],"decision-making":[11],"problems,":[12],"and":[13,42,48],"substantial":[14,213],"progress":[15],"has":[16,93,115],"achieved,":[18],"especially":[19],"in":[20,34,66,139],"autonomous":[21],"robotic":[22,63,183],"skill":[23,64],"learning.":[24],"However,":[25],"it":[26],"is":[27,133],"always":[28,46],"difficult":[29],"to":[30,56,96,118,158,231,236],"deploy":[31,232],"DRL":[32],"methods":[33],"practical":[35,237],"safety-critical":[36],"robot":[37,238],"systems,":[38],"since":[39],"the":[40,57,85,88,98,103,108,120,130,137,140,151,155,160,173,188,209,221,233],"training":[41,131],"deployment":[43],"environment":[44],"gap":[45],"exists,":[47],"this":[49],"issue":[50],"would":[51],"become":[52],"increasingly":[53],"crucial":[54],"due":[55],"ever-changing":[58],"environment.":[59],"Aiming":[60],"at":[61],"efficiently":[62],"transferring":[65],"a":[67,72,78,147,170,227],"dynamic":[68],"environment,":[69],"we":[70],"present":[71],"meta-reinforcement":[73,223],"learning":[74,113,196,224],"algorithm":[75,197,211,235],"based":[76],"on":[77,178,205],"variational":[79,89,190],"information":[80,90,191],"bottleneck.":[81],"More":[82],"specifically,":[83],"during":[84],"meta-training":[86],"stage,":[87],"bottleneck":[91,192],"first":[92],"applied":[95],"infer":[97],"complete":[99],"basic":[100,121,127,152,174],"tasks":[101,138,161,185],"whole":[104],"task":[105,141],"space,":[106],"then":[107],"maximum":[109],"entropy":[110],"regularized":[111,193],"reinforcement":[112,195],"framework":[114,225],"used":[117],"learn":[119],"skills":[122,157],"consistent":[123],"with":[124],"that":[125,187,220],"of":[126,136,150,169,172],"tasks.":[128,207],"Once":[129],"stage":[132],"completed,":[134],"all":[135],"space":[142],"can":[143,162,198],"be":[144,164],"obtained":[145,165],"by":[146,166,202],"nonlinear":[148],"combination":[149,171],"tasks,":[153],"thus,":[154],"according":[156],"accomplish":[159],"also":[163],"some":[167],"way":[168],"skills.":[175],"Empirical":[176],"results":[177,218],"several":[179],"highly":[180],"nonlinear,":[181],"high-dimensional":[182],"locomotion":[184],"show":[186],"proposed":[189,210,222],"deep":[194],"improve":[199],"sample":[200],"efficiency":[201],"200-5000":[203],"times":[204],"new":[206],"Furthermore,":[208],"achieves":[212],"asymptotic":[214],"performance":[215],"improvement.":[216],"The":[217],"indicate":[219],"makes":[226],"significant":[228],"step":[229],"forward":[230],"DRL-based":[234],"systems.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}