A Batch, Off-Policy, Actor-Critic Algorithm for Optimizing the Average Reward

Susan A. Murphy, Yanzhen Deng, Eric B. Laber, Hamid Reza Maei, Richard S. Sutton, Katie Witkiewitz

Abstract: We develop an off-policy actor-critic algorithm for learning an optimal policy from a training set composed of data from multiple individuals. This algorithm is developed with a view towards its use in mobile health.