全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...
Mathematics  2014 

Weighted Difference Approximation of Value Functions for Slow-Discounting Markov Decision Processes

Full-Text   Cite this paper   Add to My Lib

Abstract:

Processes (MDPs) often require frequent decision making, that is, taking an action every microsecond, second, or minute. Infinite horizon discount reward formulation is still relevant for a large portion of these applications, because actual time span of these problems can be months or years, during which discounting factors due to e.g. interest rates are of practical concern. In this paper, we show that, for such MDPs with discount rate $\alpha$ close to $1$, under a common ergodicity assumption, a weighted difference between two successive value function estimates obtained from the classical value iteration (VI) is a better approximation than the value function obtained directly from VI. Rigorous error bounds are established which in turn show that the approximation converges to the actual value function in a rate $(\alpha \beta)^k$ with $\beta<1$. This indicates a geometric convergence even if discount factor $\alpha \to 1$. Furthermore, we explicitly link the convergence speed to the system behaviors of the MDP using the notion of $\epsilon-$mixing time and extend our result to Q-functions. Numerical experiments are conducted to demonstrate the convergence properties of the proposed approximation scheme.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133