A Generalization Error for Q-Learning
Susan A. Murphy.
Year: 2005, Volume: 6, Issue: 37, Pages: 1073−1097
Abstract
Planning problems that involve learning a policy from a single training set of finite horizon trajectories arise in both social science and medical fields. We consider Q-learning with function approximation for this setting and derive an upper bound on the generalization error. This upper bound is in terms of quantities minimized by a Q-learning algorithm, the complexity of the approximation space and an approximation term due to the mismatch between Q-learning and the goal of learning a policy that maximizes the value function.