Search for: All records

The softmax policy gradient (PG) method, which performs gradient ascent under softmax policy parameterization, is arguably one of the de facto implementations of policy optimization in modern reinforcement learning. For$$\gamma $$$\gamma$-discounted infinite-horizon tabular Markov decision processes (MDPs), remarkable progress has recently been achieved towards establishing global convergence of softmax PG methods in finding a near-optimal policy. However, prior results fall short of delineating clear dependencies of convergence rates on salient parameters such as the cardinality of the state space$${\mathcal {S}}$$$S$and the effective horizon$$\frac{1}{1-\gamma }$$$\frac{1}{1-\gamma }$, both of which could be excessively large. In this paper, we deliver a pessimistic message regarding the iteration complexity of softmax PG methods, despite assuming access to exact gradient computation. Specifically, we demonstrate that the softmax PG method with stepsize$$\eta $$$\eta$can take$$\begin{aligned} \frac{1}{\eta } |{\mathcal {S}}|^{2^{\Omega \big (\frac{1}{1-\gamma }\big )}} ~\text {iterations} \end{aligned}$$$\begin{array}{c}\frac{1}{\eta }{\left|S\right|}^{2^{\Omega (\frac{1}{1-\gamma })}}\text{iterations}\end{array}$to converge, even in the presence of a benign policy initialization and an initial state distribution amenable to exploration (so that the distribution mismatch coefficient is not exceedingly large). This is accomplished by characterizing the algorithmic dynamics over a carefully-constructed MDP containing only three actions. Our exponential lower bound hints at the necessity of carefully adjusting update rules or enforcing proper regularization in accelerating PG methods.

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).