Stochastic primal-dual Q-learning algorithm for discounted mdps

In this work, we present a new model-free and off-policy reinforcement learning (RL) algorithm, that is capable of finding a near-optimal policy with state-action observations from arbitrary behavior policies. Our algorithm, called the stochastic primal-dual Q-learning (SPD Q-learning), hinges upon a new linear programming formulation and a dual perspective of the standard Q-learning. In contrast to previous primal-dual RL algorithms, SPD-Q learning includes a Q-function estimation step, thus allowing to recover an approximate policy from the primal solution as well as the dual solution. We prove a first-of-its-kind result that the SPD Q-learning guarantees a certain convergence rate, even when the state-action distribution under a given behavior policy is time-varying but sub-linearly converges to a stationary distribution.