Truncated Variance Reduced Value Iteration

TL;DR

This paper introduces faster randomized algorithms for computing near-optimal policies in discounted Markov decision processes, improving efficiency over previous methods by leveraging variance reduction and truncation techniques.

Contribution

The paper presents novel variance-reduced value iteration algorithms with improved time complexity for both sampling and offline settings in MDPs.

Findings

Achieves faster algorithms with improved time bounds.

Introduces variance truncation to enhance sampling procedures.

Bridges the gap between model-free and model-based methods.

Abstract

We provide faster randomized algorithms for computing an $\epsilon$-optimal policy in a discounted Markov decision process with $A_{\text{tot}}$-state-action pairs, bounded rewards, and discount factor $\gamma$. We provide an $\tilde{O}(A_{\text{tot}}[(1 - \gamma)^{-3}\epsilon^{-2} + (1 - \gamma)^{-2}])$-time algorithm in the sampling setting, where the probability transition matrix is unknown but accessible through a generative model which can be queried in $\tilde{O}(1)$-time, and an $\tilde{O}(s + (1-\gamma)^{-2})$-time algorithm in the offline setting where the probability transition matrix is known and $s$-sparse. These results improve upon the prior state-of-the-art which either ran in $\tilde{O}(A_{\text{tot}}[(1 - \gamma)^{-3}\epsilon^{-2} + (1 - \gamma)^{-3}])$ time [Sidford, Wang, Wu, Ye 2018] in the sampling setting, $\tilde{O}(s + A_{\text{tot}} (1-\gamma)^{-3})$ time [Sidford, Wang, Wu, Yang, Ye 2018] in the offline setting, or time at least quadratic in the number of states using interior point methods for linear programming. We achieve our results by building upon prior stochastic variance-reduced value iteration methods [Sidford, Wang, Wu, Yang, Ye 2018]. We provide a variant that carefully truncates the progress of its iterates to improve the variance of new variance-reduced sampling procedures that we introduce to implement the steps. Our method is essentially model-free and can be implemented in $\tilde{O}(A_{\text{tot}})$-space when given generative model access. Consequently, our results take a step in closing the sample-complexity gap between model-free and model-based methods.