Safety
Consistent Model Chasing Is Minimax Optimal: The Exact Value of Scalar Adversarial Adaptive Control under Large Parametric Uncertainty
arXiv:2608.13651v1 Announce Type: cross Abstract: We solve exactly a fundamental problem of adaptive control against adversarial disturbances: regulate the scalar system x_{t+1} = ax_t + u_t + w_t, x_
arXiv:2608.13651v1 Announce Type: cross Abstract: We solve exactly a fundamental problem of adaptive control against adversarial disturbances: regulate the scalar system x_{t+1} = ax_t + u_t + w_t, x_0=0, |w|_infty le 1, where the constant pole a in [-Delta, Delta] is unknown in sign and magnitude and Delta is arbitrarily large. Elementary as the system looks, the least worst-case peak |x|_infty that a causal controller can guarantee against an adversarial pair (a, w) (the value of this game) has, to our knowledge, never been determined for any adaptive control problem with parametric uncertainty of arbitrary size under this criterion; existing theory supplies stability certificates, gain bounds, and regret rates, not the value. That value is gamma^star(Delta) = 1 + Delta for every Delta>0. The summand 1 is the irreducible price of the disturbance, and Delta the exact price of a single, unavoidable identification spike. The optimal policy is certainty-equivalent deadbeat control at the midpoint of the set-membership consistent interval, an instance of the robust oracle imes consistent model chasing architecture. The architecture is forced, not merely sufficient: writing heta_t := -u_t/x_t exhibits every causal controller as an oracle-selector composition, and optimality pins the selector to the midpoint at the critical histories. The standard tools, classical and modern, each fail quantifiably: probing is punished before it pays, commitment is fatal at sub-disturbance excitation once adaptation is necessary, optimism degenerates to tie-breaking or pays asymptotically at least twice the optimum, and regret certificates are blind to the worst-case peak in both directions. The optimal law contains no exploration mechanism, its learning purely passive. These results give the first exact optimality certificate for consistent model chasing as a design principle for adversarial adaptive control.
Related
- Near-Optimal Regret for the Safe Learning-based Control of the Constrained Linear Quadratic Regulator
- A Spectral Filtering Approach to Regret Analysis of Distributed Online Control for Linear Dynamical Systems
- End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers
Source: arXiv cs.LG | 2026-08-17