Online Inference for Quantile Distributional Reinforcement Learning

arXiv:2608.12973v3 Announce Type: replace-cross Abstract: In this paper, we study online statistical inference for quantile-based distributional policy evaluation, which aims to characterize the distribution of discounted cumulative rewards under a given policy. To obtain a finite-dimensional representation of the return distribution, we consider the fixed point $\bm\eta_m$ of the quantile-projected distributional Bellman equation, parameterized by the quantile vector $\bm\theta_m$. We develop two online inference procedures for $\bm\theta_m$, covering synchronous and asynchronous sampling from a generative model as well as Markovian data. The first method uses the trajectory of quantile temporal-difference learning (QTD). We establish functional central limit theorems for the partial sums of QTD iterates and construct a recursively computable random-scaling statistic. The resulting confidence intervals have asymptotically exact coverage at deterministic horizons, with length of order $T^{-1/2}$ in probability. The second method constructs anytime-valid confidence intervals directly from samples. Exploiting the monotonicity of the quantile Bellman map, we develop a computationally explicit coordinate-shaving algorithm with finite-sample simultaneous coverage. Under positive limiting state-visit frequencies, the resulting confidence intervals have lengths of order $\sqrt{\log\log T/T}$, which we establish as classwise optimal through a matching lower bound. Together, these results provide complementary guarantees for online inference in quantile distributional reinforcement learning, combining asymptotically exact fixed-horizon inference with finite-sample anytime validity.