pith. sign in

arxiv: 1004.2027 · v2 · pith:LGKWV5JUnew · submitted 2010-04-12 · 💻 cs.LG · cs.AI· cs.SY· math.OC· stat.ML

Dynamic Policy Programming

classification 💻 cs.LG cs.AIcs.SYmath.OCstat.ML
keywords policyapproximateerrorinfty-normiterationboundsdynamiclearning
0
0 comments X
read the original abstract

In this paper, we propose a novel policy iteration method, called dynamic policy programming (DPP), to estimate the optimal policy in the infinite-horizon Markov decision processes. We prove the finite-iteration and asymptotic l\infty-norm performance-loss bounds for DPP in the presence of approximation/estimation error. The bounds are expressed in terms of the l\infty-norm of the average accumulated error as opposed to the l\infty-norm of the error in the case of the standard approximate value iteration (AVI) and the approximate policy iteration (API). This suggests that DPP can achieve a better performance than AVI and API since it averages out the simulation noise caused by Monte-Carlo sampling throughout the learning process. We examine this theoretical results numerically by com- paring the performance of the approximate variants of DPP with existing reinforcement learning (RL) methods on different problem domains. Our results show that, in all cases, DPP-based algorithms outperform other RL methods by a wide margin.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.