Randomized Optimal Switching Problem and Related Mirror Descent Flow
We study continuous-time reinforcement learning for the optimal switching problem, in which a decision-maker controls a diffusion process by switching among finitely many regimes, incurring both running and transition costs. To enable exploration, we relax the classical deterministic switching control to a randomized framework, where the switching decisions are governed by a continuous-time Markov chain with state-dependent generator, and augment the cost functional with a KL-divergence regularization weighted by a temperature parameter $λ$. Under mild assumptions on the coefficients, we establish that the regularized value function is the unique smooth solution of an elliptic Hamilton--Jacobi--Bellman system, and derive an explicit optimal Gibbs policy given by an exponential transformation of the value function differences across modes. We further prove that the regularized value function approximates the classical optimal value function with error of order $O\left(λ\log \frac{1}λ\right)$, which is consistent with analogous bounds established in other entropy-regularized control problems and is believed to be sharp. To solve the regularized problem numerically, we introduce a mirror descent flow in the dual logarithmic policy space, prove its well-posedness and the monotonic decrease of the value function along the flow, and establish quantitative error bound to the classical optimal value function. For a constant temperature scheduler, the convergence rate is of order $O\left(\frac{1}{e^{λs} - 1}+λ\log\frac1λ\right)$, while under the annealing scheduler $λ_s = \frac{1}{\sqrt{1+s}}$, we obtain the rate $O\left(\frac{\log s}{\sqrt{s}}\right)$, which decays to zero as the flow time $s \to \infty$.