{"id":"https://openalex.org/W7124150836","doi":"https://doi.org/10.1109/tpami.2026.3653866","title":"Reinforced Refinement With Self-Aware Expansion for End-to-End Autonomous Driving","display_name":"Reinforced Refinement With Self-Aware Expansion for End-to-End Autonomous Driving","publication_year":2026,"publication_date":"2026-01-14","ids":{"openalex":"https://openalex.org/W7124150836","doi":"https://doi.org/10.1109/tpami.2026.3653866","pmid":"https://pubmed.ncbi.nlm.nih.gov/41533609"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3653866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3653866","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5007929452","display_name":"Haochen Liu","orcid":"https://orcid.org/0000-0002-3628-8777"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haochen Liu","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-3628-8777","affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianyu Li","orcid":"https://orcid.org/0009-0008-3838-160X"},"institutions":[{"id":"https://openalex.org/I8679417","display_name":"Hong Kong Metropolitan University","ror":"https://ror.org/0349bsm71","country_code":"HK","type":"education","lineage":["https://openalex.org/I8679417"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tianyu Li","raw_affiliation_strings":["OpenDriveLab, School of Computing and Data Science, The University of Hong Kong, Pok Fu Lam, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0008-3838-160X","affiliations":[{"raw_affiliation_string":"OpenDriveLab, School of Computing and Data Science, The University of Hong Kong, Pok Fu Lam, Hong Kong","institution_ids":["https://openalex.org/I8679417","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024672407","display_name":"Haohan Yang","orcid":"https://orcid.org/0000-0002-1545-2793"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haohan Yang","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-1545-2793","affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123049325","display_name":"Li Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I8679417","display_name":"Hong Kong Metropolitan University","ror":"https://ror.org/0349bsm71","country_code":"HK","type":"education","lineage":["https://openalex.org/I8679417"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Li Chen","raw_affiliation_strings":["OpenDriveLab, School of Computing and Data Science, The University of Hong Kong, Pok Fu Lam, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OpenDriveLab, School of Computing and Data Science, The University of Hong Kong, Pok Fu Lam, Hong Kong","institution_ids":["https://openalex.org/I8679417","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109786205","display_name":"Caojun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2802974365","display_name":"Shanghai Innovative Research Center of Traditional Chinese Medicine","ror":"https://ror.org/01gnagj68","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802974365"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caojun Wang","raw_affiliation_strings":["Shanghai Innovation Institute, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-0113-2373","affiliations":[{"raw_affiliation_string":"Shanghai Innovation Institute, Shanghai, China","institution_ids":["https://openalex.org/I2802974365"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047425404","display_name":"Ke Guo","orcid":"https://orcid.org/0000-0003-0764-9577"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ke Guo","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122998138","display_name":"Haochen Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I8679417","display_name":"Hong Kong Metropolitan University","ror":"https://ror.org/0349bsm71","country_code":"HK","type":"education","lineage":["https://openalex.org/I8679417"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Haochen Tian","raw_affiliation_strings":["OpenDriveLab, School of Computing and Data Science, The University of Hong Kong, Pok Fu Lam, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OpenDriveLab, School of Computing and Data Science, The University of Hong Kong, Pok Fu Lam, Hong Kong","institution_ids":["https://openalex.org/I8679417","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043784915","display_name":"H. Y. Li","orcid":"https://orcid.org/0009-0009-2672-2662"},"institutions":[{"id":"https://openalex.org/I2802974365","display_name":"Shanghai Innovative Research Center of Traditional Chinese Medicine","ror":"https://ror.org/01gnagj68","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802974365"]},{"id":"https://openalex.org/I8679417","display_name":"Hong Kong Metropolitan University","ror":"https://ror.org/0349bsm71","country_code":"HK","type":"education","lineage":["https://openalex.org/I8679417"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Hongchen Li","raw_affiliation_strings":["OpenDriveLab, School of Computing and Data Science, The University of Hong Kong, Pok Fu Lam, Hong Kong","Shanghai Innovation Institute, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OpenDriveLab, School of Computing and Data Science, The University of Hong Kong, Pok Fu Lam, Hong Kong","institution_ids":["https://openalex.org/I8679417","https://openalex.org/I889458895"]},{"raw_affiliation_string":"Shanghai Innovation Institute, Shanghai, China","institution_ids":["https://openalex.org/I2802974365"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123002136","display_name":"Hongyang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I2802974365","display_name":"Shanghai Innovative Research Center of Traditional Chinese Medicine","ror":"https://ror.org/01gnagj68","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802974365"]},{"id":"https://openalex.org/I8679417","display_name":"Hong Kong Metropolitan University","ror":"https://ror.org/0349bsm71","country_code":"HK","type":"education","lineage":["https://openalex.org/I8679417"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Hongyang Li","raw_affiliation_strings":["OpenDriveLab, School of Computing and Data Science, The University of Hong Kong, Pok Fu Lam, Hong Kong","Shanghai Innovation Institute, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OpenDriveLab, School of Computing and Data Science, The University of Hong Kong, Pok Fu Lam, Hong Kong","institution_ids":["https://openalex.org/I8679417","https://openalex.org/I889458895"]},{"raw_affiliation_string":"Shanghai Innovation Institute, Shanghai, China","institution_ids":["https://openalex.org/I2802974365"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120982428","display_name":"Chen Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Lv","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6897-4512","affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06331195,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"5","first_page":"5774","last_page":"5792"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5742999911308289,"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":0.5742999911308289,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.18809999525547028,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10653","display_name":"Robot Manipulation and Learning","score":0.05990000069141388,"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":0.8245000243186951},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5946999788284302},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5109000205993652},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4869000017642975},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4632999897003174},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.4226999878883362},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.36640000343322754},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.3495999872684479},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.34850001335144043}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8245000243186951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7717999815940857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6496000289916992},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5946999788284302},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5598999857902527},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5109000205993652},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4869000017642975},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4632999897003174},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.3125},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C167740415","wikidata":"https://www.wikidata.org/wiki/Q2876213","display_name":"Aerospace","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2026.3653866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3653866","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41533609","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41533609","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":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:dr.ntu.edu.sg:10356/212482","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/212482","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7188244462013245,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G7507727940","display_name":null,"funder_award_id":"MOE-T2EP50222-0002","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"},{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"End-to-end":[0],"autonomous":[1,214],"driving":[2,64,100,105,134,166],"has":[3],"emerged":[4],"as":[5],"a":[6,34,47,88,129],"promising":[7],"paradigm":[8],"for":[9,102,141,212],"directly":[10],"mapping":[11],"sensor":[12],"inputs":[13],"to":[14,30,50,62,156],"planning":[15],"maneuvers":[16],"using":[17,152],"learning-based":[18],"modular":[19],"integrations.":[20],"However,":[21],"existing":[22],"imitation":[23,131],"learning":[24,44,90,132,154],"(IL)-based":[25],"models":[26],"suffer":[27],"from":[28],"generalization":[29],"hard":[31,52,95,160],"cases,":[32,65],"and":[33,73,110,190,198],"lack":[35],"of":[36,70,209],"corrective":[37],"feedback":[38],"loop":[39],"under":[40],"post-deployment.":[41],"While":[42],"reinforcement":[43,108,153],"(RL)":[45,155],"offers":[46],"potential":[48],"solution":[49],"tackle":[51],"cases":[53,140],"with":[54,84,125],"optimality,":[55],"it":[56],"is":[57],"often":[58],"hindered":[59],"by":[60],"overfitting":[61],"specific":[63],"resulting":[66],"in":[67,159,187,195],"catastrophic":[68],"forgetting":[69],"generalizable":[71,99],"knowledge":[72],"sample":[74],"inefficiency.":[75],"To":[76],"overcome":[77],"these":[78],"challenges,":[79],"we":[80],"propose":[81],"Reinforced":[82,146],"Refinement":[83],"Self-aware":[85,169],"Expansion":[86,171],"(R2SE),":[87],"novel":[89],"pipeline":[91],"that":[92,113],"constantly":[93],"refines":[94],"domain":[96,162],"while":[97,136,163],"keeping":[98],"policy":[101,111,200],"model-agnostic":[103],"end-to-end":[104],"systems.":[106],"Through":[107],"fine-tuning":[109],"expansion":[112],"facilitates":[114],"continuous":[115,182],"improvement,":[116],"R2SE":[117],"features":[118],"three":[119],"key":[120],"components:":[121],"1)":[122],"Generalist":[123],"Pretraining":[124],"hard-case":[126],"allocation":[127],"trains":[128],"generalist":[130,179],"(IL)":[133],"system":[135],"dynamically":[137,172],"identifying":[138],"failure-prone":[139],"targeted":[142],"refinement;":[143],"2)":[144],"Residual":[145],"Specialist":[147],"Fine-tuning":[148],"optimizes":[149],"residual":[150],"corrections":[151],"improve":[157],"performance":[158,183],"case":[161],"preserving":[164],"global":[165],"knowledge;":[167],"3)":[168],"Adapter":[170],"integrates":[173],"specialist":[174],"policies":[175],"back":[176],"into":[177],"the":[178,207],"model,":[180],"enhancing":[181],"improvement.":[184],"Experimental":[185],"results":[186],"closed-loop":[188],"simulation":[189],"real-world":[191],"datasets":[192],"demonstrate":[193],"improvements":[194],"generalization,":[196],"safety,":[197],"long-horizon":[199],"robustness":[201],"over":[202],"state-of-the-art":[203],"E2E":[204],"systems,":[205],"highlighting":[206],"effectiveness":[208],"reinforce":[210],"refinement":[211],"scalable":[213],"driving.":[215]},"counts_by_year":[],"updated_date":"2026-04-04T06:10:10.580331","created_date":"2026-01-15T00:00:00"}