Quantum speedups for convex dynamic programming

Abstract

We present a quantum algorithm to solve dynamic programming problems with convex value functions. For linear discrete-time systems with a $d$-dimensional state space of size $N$, the proposed algorithm outputs a quantum-mechanical representation of the value function in time $O(T \gamma^{dT}\mathrm{polylog}(N,(T/\varepsilon)^{d}))$,where$\varepsilon$ is the accuracy of the solution, $T$ is the time horizon, and $\gamma$ is a problem-specific parameter depending on the condition numbers of the cost functions. This allows us to evaluate the value function at any fixed state in time $O(T{\gamma }^{dT}\sqrt{N}\mathrm{polylog}(N,(T/\epsilon {)}^d))$, and the corresponding optimal action can be recovered by solving a convex program. The class of optimization problems to which our algorithm can be applied includes provably hard stochastic dynamic programs. Finally, we show that the algorithm obtains a quadratic speedup (up to polylogarithmic factors) compared to the classical Bellman approach on some dynamic programs with continuous state space that have $\gamma =1$.