학술논문
Stochastic Halpern iteration in normed spaces and applications to reinforcement learning
Document Type
Working Paper
Author
Source
Subject
Language
Abstract
We analyze the oracle complexity of the stochastic Halpern iteration with variance reduction, where we aim to approximate fixed-points of nonexpansive and contractive operators in a normed finite-dimensional space. We show that if the underlying stochastic oracle is with uniformly bounded variance, our method exhibits an overall oracle complexity of $\tilde{O}(\varepsilon^{-5})$, improving recent rates established for the stochastic Krasnoselskii-Mann iteration. Also, we establish a lower bound of $\Omega(\varepsilon^{-3})$, which applies to a wide range of algorithms, including all averaged iterations even with minibatching. Using a suitable modification of our approach, we derive a $O(\varepsilon^{-2}(1-\gamma)^{-3})$ complexity bound in the case in which the operator is a $\gamma$-contraction. As an application, we propose new synchronous algorithms for average reward and discounted reward Markov decision processes. In particular, for the average reward, our method improves on the best-known sample complexity.
Comment: Added references, typos corrected
Comment: Added references, typos corrected