arXiv stat.ML
· Papers
Online Inference for Quantile Temporal Difference Learning in Distributional Reinforcement Learning
arXiv:2608.12973v1 Announce Type: new Abstract: In this paper, we study how to perform statistical inference for quantile temporal difference learning (QTD) in distributional reinforcement learning. Assuming access to a generative model, we first establish functional central limit theorems for both synchronous and asyn