Sciweavers

LICS
2007
IEEE

Limits of Multi-Discounted Markov Decision Processes

14 years 4 months ago
Limits of Multi-Discounted Markov Decision Processes
Markov decision processes (MDPs) are controllable discrete event systems with stochastic transitions. The payoff received by the controller can be evaluated in different ways, depending on the payoff function the MDP is equipped with. For example a mean–payoff function evaluates average performance, whereas a discounted payoff function gives more weights to earlier performance by means of a discount factor. Another well–known example is the parity payoff function which is used to encode logical specifications [14]. Surprisingly, parity and mean–payoff MDPs share two non–trivial properties: they both have pure stationary optimal strategies [4, 15] and they both are approximable by discounted MDPs with multiple discount factors (multi– discounted MDPs) [5, 15]. In this paper we unify and generalize these results. We introduce a new class of payoff functions called the priority weighted payoff functions, which are generalization of both parity and mean–payoff functions. We p...
Hugo Gimbert, Wieslaw Zielonka
Added 04 Jun 2010
Updated 04 Jun 2010
Type Conference
Year 2007
Where LICS
Authors Hugo Gimbert, Wieslaw Zielonka
Comments (0)