Tight Performance Bounds for Approximate Modified Policy Iteration with Non-Stationary Policies - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2013

Tight Performance Bounds for Approximate Modified Policy Iteration with Non-Stationary Policies

Boris Lesner
  • Function : Author
  • PersonId : 933391
Bruno Scherrer

Abstract

We consider approximate dynamic programming for the infinite-horizon stationary $\gamma$-discounted optimal control problem formalized by Markov Decision Processes. While in the exact case it is known that there always exists an optimal policy that is stationary, we show that when using value function approximation, looking for a non-stationary policy may lead to a better performance guarantee. We define a non-stationary variant of MPI that unifies a broad family of approximate DP algorithms of the literature. For this algorithm we provide an error propagation analysis in the form of a performance bound of the resulting policies that can improve the usual performance bound by a factor $O\left(1-\gamma\right)$, which is significant when the discount factor $\gamma$ is close to 1. Doing so, our approach unifies recent results for Value and Policy Iteration. Furthermore, we show, by constructing a specific deterministic MDP, that our performance guarantee is tight.
Fichier principal
Vignette du fichier
report.pdf (570.15 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00815996 , version 1 (19-04-2013)

Identifiers

Cite

Boris Lesner, Bruno Scherrer. Tight Performance Bounds for Approximate Modified Policy Iteration with Non-Stationary Policies. 2013. ⟨hal-00815996⟩
182 View
232 Download

Altmetric

Share

Gmail Facebook X LinkedIn More