Search for: All records

This paper studies a central issue in modern reinforcement learning, the sample efficiency, and makes progress toward solving an idealistic scenario that assumes access to a generative model or a simulator. Despite a large number of prior works tackling this problem, a complete picture of the trade-offs between sample complexity and statistical accuracy has yet to be determined. In particular, all prior results suffer from a severe sample size barrier in the sense that their claimed statistical guarantees hold only when the sample size exceeds some enormous threshold. The current paper overcomes this barrier and fully settles this problem; more specifically, we establish the minimax optimality of the model-based approach for any given target accuracy level. To the best of our knowledge, this work delivers the first minimax-optimal guarantees that accommodate the entire range of sample sizes (beyond which finding a meaningful policy is information theoretically infeasible). 

This paper investigates a model-free algorithm of broad interest in reinforcement learning, namely, Q-learning. Whereas substantial progress had been made toward understanding the sample efficiency of Q-learning in recent years, it remained largely unclear whether Q-learning is sample-optimal and how to sharpen the sample complexity analysis of Q-learning. In this paper, we settle these questions: (1) When there is only a single action, we show that Q-learning (or, equivalently, TD learning) is provably minimax optimal. (2) When there are at least two actions, our theory unveils the strict suboptimality of Q-learning and rigorizes the negative impact of overestimation in Q-learning. Our theory accommodates both the synchronous case (i.e., the case in which independent samples are drawn) and the asynchronous case (i.e., the case in which one only has access to a single Markovian trajectory). 

Natural policy gradient (NPG) methods are among the most widely used policy optimization algorithms in contemporary reinforcement learning. This class of methods is often applied in conjunction with entropy regularization—an algorithmic scheme that encourages exploration—and is closely related to soft policy iteration and trust region policy optimization. Despite the empirical success, the theoretical underpinnings for NPG methods remain limited even for the tabular setting. This paper develops nonasymptotic convergence guarantees for entropy-regularized NPG methods under softmax parameterization, focusing on discounted Markov decision processes (MDPs). Assuming access to exact policy evaluation, we demonstrate that the algorithm converges linearly—even quadratically, once it enters a local region around the optimal policy—when computing optimal value functions of the regularized MDP. Moreover, the algorithm is provably stable vis-à-vis inexactness of policy evaluation. Our convergence results accommodate a wide range of learning rates and shed light upon the role of entropy regularization in enabling fast convergence.