Blackwell Optimality in Markov Decision Processes with Partial Observation
نویسندگان
چکیده
We prove the existence of Blackwell ε-optimal strategies in finite Markov Decision Processes with partial observation. ∗Laboratoire d’Analyse Geometrie et Applications Institut Galilée, Université Paris Nord, avenue Jean Baptiste Clément, 93430 Villetaneuse, France. e-mail: [email protected] †Department of Managerial Economics and Decision Sciences, Kellogg School of Management, Northwestern University, Evanston IL 60208. e-mail: [email protected] ‡GRAPE, Université Montesquieu-Bordeaux 4, and Laboratoire d’Econométrie de l’Ecole Polytechnique, 1 rue Descartes, 75 005 Paris, France. e-mail: [email protected]
منابع مشابه
Blackwell Optimality in Markov Decision Processes with Partial Observation by Dinah Rosenberg,
A Blackwell ε-optimal strategy in a Markov Decision Process is a strategy that is ε-optimal for every discount factor sufficiently close to 1. We prove the existence of Blackwell ε-optimal strategies in finite Markov Decision Processes with partial observation. 1. Introduction. A well-known result by Blackwell [3] states that, in any Markov Decision Process (MDP hereafter) with finitely many st...
متن کاملSensitive Discount Optimality via Nested Linear Programs for Ergodic Markov Decision Processes
In this paper we discuss the sensitive discount opti-mality for Markov decision processes. The n-discount optimality is a reened selective criterion, that is a generalization of the average optimality and the bias optimality. Our approach is based on the system of nested linear programs. In the last section we provide an algorithm for the computation of the Blackwell optimal policy. The n-disco...
متن کاملApplying Blackwell optimality: priority mean-payoff games as limits of multi-discounted games
We define and examine priority mean-payoff games — a natural extension of parity games. By adapting the notion of Blackwell optimality borrowed from the theory of Markov decision processes we show that priority mean-payoff games can be seen as a limit of special multi-discounted games.
متن کاملBounded Parameter Markov Decision Processes with Average Reward Criterion
Bounded parameter Markov Decision Processes (BMDPs) address the issue of dealing with uncertainty in the parameters of a Markov Decision Process (MDP). Unlike the case of an MDP, the notion of an optimal policy for a BMDP is not entirely straightforward. We consider two notions of optimality based on optimistic and pessimistic criteria. These have been analyzed for discounted BMDPs. Here we pro...
متن کاملBlackwell Optimality for Controlled Diffusion Processes
In this paper we study m-discount optimality (m ≥ −1) and Blackwell optimality for a general class of controlled (Markov) diffusion processes. To this end, a key step is to express the expected discounted reward function as a Laurent series, and then search certain control policies that lexicographically maximize themth coefficient of this series form = −1, 0, 1, . . . .This approach naturally ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2000