Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation

Daniel Vial, Advait Parulekar, Sanjay Shakkottai, R. Srikant

Abstract: We propose an algorithm that uses linear function approximation (LFA) for stochastic shortest path (SSP). Under minimal assumptions, it obtains sublinear regret, is computationally efficient, and u...