Robust Control with Gradient Uncertainty

Abstract

We introduce a novel extension to robust control theory that explicitly addresses uncertainty in the value function's gradient, a form of uncertainty endemic to applications like reinforcement learning where value functions are approximated. We formulate a zero-sum dynamic game where an adversary perturbs both system dynamics and the value function gradient, leading to a new, highly nonlinear partial differential equation: the Hamilton-Jacobi-Bellman-Isaacs Equation with Gradient Uncertainty (GU-HJBI). We establish its well-posedness by proving a comparison principle for its viscosity solutions under a uniform ellipticity condition. Our analysis of the linear-quadratic (LQ) case yields a key insight: we prove that the classical quadratic value function assumption fails for any non-zero gradient uncertainty, fundamentally altering the problem structure. A formal perturbation analysis characterizes the non-polynomial correction to the value function and the resulting nonlinearity of the optimal control law, which we validate with numerical studies. Finally, we bridge theory to practice by proposing a novel Gradient-Uncertainty-Robust Actor-Critic (GURAC) algorithm, accompanied by an empirical study demonstrating its effectiveness in stabilizing training. This work provides a new direction for robust control, holding significant implications for fields where function approximation is common, including reinforcement learning and computational finance.