{"id":"W4417297121","doi":"10.48550/arxiv.2512.10906","title":"Distributionally Robust Regret Optimal Control Under Moment-Based Ambiguity Sets","year":2025,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Cornell Atkinson Center for Sustainability, Cornell University; David R. Atkinson Center for a Sustainable Future , Cornell University","keywords":"Subgradient method; Semidefinite programming; Convex optimization; Optimal control; Regret; Minimax; Convexity; Probability distribution; Ambiguity; Stochastic control","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.003995062,0.001377533,0.001845317,0.001594034,0.001554087,0.0007848347,0.005589632,0.001317516,0.003786206],"category_scores_gemma":[0.00177354,0.001486707,0.001375208,0.004637663,0.002151005,0.001051213,0.003585371,0.003012305,0.001044987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003373088,"about_ca_system_score_gemma":0.004911563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003008405,"about_ca_topic_score_gemma":0.0001302159,"domain_scores_codex":[0.9874143,0.001885402,0.001547923,0.005024911,0.002036121,0.00209137],"domain_scores_gemma":[0.9863482,0.004011628,0.001296963,0.003596771,0.003561586,0.001184911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001635204,0.0006803949,0.002590977,0.00008421352,0.0004504118,0.000734869,0.00003279379,0.9754928,0.0000191301,0.01506209,0.001677922,0.001539247],"study_design_scores_gemma":[0.00646509,0.0002637149,0.008666747,0.0003164489,0.0003488981,0.000007005239,0.000543217,0.9471438,0.0001941024,0.02985957,0.004791372,0.001400057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03935055,0.000170031,0.9480064,0.001534387,0.001493148,0.001783261,0.005818948,0.0001898633,0.001653395],"genre_scores_gemma":[0.9694054,0.0002442949,0.002215625,0.0003541417,0.0001681622,0.00001124299,0.0004742747,0.00004717921,0.02707972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9457908,"threshold_uncertainty_score":0.999979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1950033316790077,"score_gpt":0.2983135814725048,"score_spread":0.103310249793497,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}