Sharp Critical Minimax Laws and No-Learning Thresholds in Continuous-Time Adaptive Control

arXiv:2609.33154 · math.OC, cs.LG · Submitted 2026-09-27 · Read on arXiv

math.OC, cs.LG

Submitted: 2026-09-27

Updated: 2026-09-27

Terminology

• Regret — 14× in this paper · explained in 3 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Admissibility — 3× in this paper · explained in 2 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Minimax Regret — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models
• A sequential estimation problem with control and discretionary stopping
• On the Fundamental Limits of Adaptive Sensing
• How to sample and when to stop sampling: The generalized Wald problem and minimax policies
• Continuous time asymptotic representations for adaptive experiments
• Limiting laws associated with Brownian motion perturbated by normalized exponential weights I
• On occupation times of one-dimensional diffusions
• Optimal adaptive control with separable drift uncertainty

Related papers

• Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
• Adam-HNAG: A Convergent Reformulation of Adam with Accelerated Rate
• Incremental Learning in Mirror Flows
• Online Control via Counterfactual Tracking
• Asynchronous Replanning in Two Population Linear Quadratic Mean Field Games: Information Requirements and Stability
• Petrov-Galerkin operator inference with application to stability-encouraging identification