Sciweavers

Share
ICALP
2005
Springer

Recursive Markov Decision Processes and Recursive Stochastic Games

9 years 11 months ago
Recursive Markov Decision Processes and Recursive Stochastic Games
We introduce Recursive Markov Decision Processes (RMDPs) and Recursive Simple Stochastic Games (RSSGs), which are classes of (finitely presented) countable-state MDPs and zero-sum turn-based (perfect information) stochastic games. They extend standard finite-state MDPs and stochastic games with a recursion feature. We study the decidability and computational complexity of these games under termination objectives for the two players: one player’s goal is to maximize the probability of termination at a given exit, while the other player’s goal is to minimize this probability. In the quantitative termination problems, given an RMDP (or RSSG) and probability p, we wish to decide whether the value of such a termination game is at least p (or at most p); in the qualitative termination problem we wish to decide whether the value is
Kousha Etessami, Mihalis Yannakakis
Added 27 Jun 2010
Updated 27 Jun 2010
Type Conference
Year 2005
Where ICALP
Authors Kousha Etessami, Mihalis Yannakakis
Comments (0)
books