{"id":"https://openalex.org/W4415257571","doi":"https://doi.org/10.48550/arxiv.2510.11899","title":"ADARL: Adaptive Low-Rank Structures for Robust Policy Learning under Uncertainty","display_name":"ADARL: Adaptive Low-Rank Structures for Robust Policy Learning under Uncertainty","publication_year":2025,"publication_date":"2025-10-13","ids":{"openalex":"https://openalex.org/W4415257571","doi":"https://doi.org/10.48550/arxiv.2510.11899"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2510.11899","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.11899","pdf_url":"https://arxiv.org/pdf/2510.11899","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.11899","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100734069","display_name":"Chenliang Li","orcid":"https://orcid.org/0000-0003-3144-6374","observed_orcids":["https://orcid.org/0000-0003-3144-6374","https://orcid.org/0000-0002-7443-6267"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chenliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043865073","display_name":"Junyu Leng","orcid":"https://orcid.org/0000-0002-8931-5783","observed_orcids":["https://orcid.org/0000-0002-8931-5783"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leng, Junyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101588120","display_name":"Jiaxiang Li","orcid":"https://orcid.org/0009-0005-4276-5612","observed_orcids":["https://orcid.org/0009-0005-4276-5612","https://orcid.org/0000-0002-7384-1199"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jiaxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076743577","display_name":"Youbang Sun","orcid":"https://orcid.org/0000-0003-2494-8552","observed_orcids":["https://orcid.org/0000-0003-2494-8552"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Youbang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064612677","display_name":"Shixiang Chen","orcid":"https://orcid.org/0000-0002-3261-0714","observed_orcids":["https://orcid.org/0000-0002-3261-0714"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Shixiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040922600","display_name":"Shahin Shahrampour","orcid":"https://orcid.org/0000-0003-3093-8510","observed_orcids":["https://orcid.org/0000-0003-3093-8510"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shahrampour, Shahin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087676937","display_name":"Alfredo Garcia","orcid":"https://orcid.org/0000-0002-8902-6834","observed_orcids":["https://orcid.org/0000-0002-8902-6834"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Garcia, Alfredo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":9.999999747378752e-05,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0,"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/robust-reinforcement-learning","display_name":"robust reinforcement learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/epistemic-uncertainty","display_name":"epistemic uncertainty","score":0.9580000042915344},{"id":"https://openalex.org/keywords/model-uncertainty","display_name":"model uncertainty","score":0.6759999990463257},{"id":"https://openalex.org/keywords/wasserstein-ball","display_name":"Wasserstein ball","score":0.7260000109672546},{"id":"https://openalex.org/keywords/bi-level-optimization","display_name":"bi-level optimization","score":0.8629999756813049},{"id":"https://openalex.org/keywords/bias-variance-trade-off","display_name":"bias-variance trade-off","score":0.9679999947547913},{"id":"https://openalex.org/keywords/continuous-control","display_name":"continuous control","score":0.6570000052452087},{"id":"https://openalex.org/keywords/mujoco","display_name":"MuJoCo","score":0.796999990940094}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7056999802589417},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5795000195503235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5546000003814697},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5138999819755554},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43149998784065247},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.3596999943256378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3269999921321869},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3061999976634979},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.27459999918937683},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2547000050544739},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.11899","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.11899","pdf_url":"https://arxiv.org/pdf/2510.11899","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2510.11899","doi":"https://doi.org/10.48550/arxiv.2510.11899","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.11899","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.11899","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.11899","pdf_url":"https://arxiv.org/pdf/2510.11899","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7154230169","https://openalex.org/W4384652381","https://openalex.org/W3035794811","https://openalex.org/W3217647572","https://openalex.org/W3168872570","https://openalex.org/W7214211367","https://openalex.org/W4399759260","https://openalex.org/W3177193849","https://openalex.org/W2964751386","https://openalex.org/W2914994663"],"abstract_inverted_index":{"Robust":[0],"reinforcement":[1],"learning":[2],"(Robust":[3],"RL)":[4],"seeks":[5],"to":[6,86],"handle":[7],"epistemic":[8],"uncertainty":[9],"in":[10],"environment":[11],"dynamics,":[12],"but":[13,136],"existing":[14],"approaches":[15],"often":[16],"rely":[17],"on":[18,112],"nested":[19],"min--max":[20],"optimization,":[21],"which":[22],"is":[23],"computationally":[24],"expensive":[25],"and":[26,128,158],"yields":[27],"overly":[28],"conservative":[29],"policies.":[30],"We":[31],"propose":[32],"\\textbf{Adaptive":[33],"Rank":[34],"Representation":[35],"(AdaRL)},":[36],"a":[37,70,74,95],"bi-level":[38],"optimization":[39,62],"framework":[40],"that":[41,118,150],"improves":[42],"robustness":[43,107],"by":[44],"aligning":[45],"policy":[46,61,92,153],"complexity":[47],"with":[48,66],"the":[49,53,56,78,84,88,140,144],"intrinsic":[50,141],"dimension":[51],"of":[52,143],"task.":[54],"At":[55,77],"lower":[57],"level,":[58,80],"AdaRL":[59,119],"performs":[60],"under":[63,164],"fixed-rank":[64,124],"constraints":[65],"dynamics":[67,104],"sampled":[68],"from":[69],"Wasserstein":[71],"ball":[72],"around":[73],"centroid":[75],"model.":[76],"upper":[79],"it":[81],"adaptively":[82],"adjusts":[83],"rank":[85,142],"balance":[87],"bias--variance":[89],"trade-off,":[90],"projecting":[91],"parameters":[93],"onto":[94],"low-rank":[96,152],"manifold.":[97],"This":[98],"design":[99],"avoids":[100],"solving":[101],"adversarial":[102],"worst-case":[103],"while":[105],"ensuring":[106],"without":[108],"over-parameterization.":[109],"Empirical":[110],"results":[111,148],"MuJoCo":[113],"continuous":[114],"control":[115],"benchmarks":[116],"demonstrate":[117],"not":[120],"only":[121],"consistently":[122],"outperforms":[123],"baselines":[125],"(e.g.,":[126,133],"SAC)":[127],"state-of-the-art":[129],"robust":[130,162],"RL":[131,163],"methods":[132],"RNAC,":[134],"Parseval),":[135],"also":[137],"converges":[138],"toward":[139],"underlying":[145],"tasks.":[146],"These":[147],"highlight":[149],"adaptive":[151],"representations":[154],"provide":[155],"an":[156],"efficient":[157],"principled":[159],"alternative":[160],"for":[161],"model":[165],"uncertainty.":[166]},"counts_by_year":[],"updated_date":"2026-10-09T09:14:12.587421","created_date":"2025-10-17T00:00:00"}