Uncertainty in Artificial Intelligence
First Name   Last Name   Password   Forgot Password   Log in!
    Proceedings         Authors   Author's Info   Article details         Search    
Closed-form Solutions to a Subclass of Continuous Stochastic Games via Symbolic Dynamic Programming
Shamin Kinathil, Scott Sanner, Nicolas Della Penna
Abstract:
Zero-sum stochastic games provide a formal- ism to study competitive sequential interactions between two agents with diametrically oppos- ing goals and evolving state. A solution to such games with discrete state was presented by Littman (Littman, 1994). The continuous state version of this game remains unsolved. In many instances continuous state solutions require non- linear optimisation, a problem for which closed- form solutions are generally unavailable. We present an exact closed-form solution to a sub- class of zero-sum continuous stochastic games that can be solved as a parameterised linear pro- gram by utilising symbolic dynamic program- ming. This novel technique is applied to calcu- late exact solutions to a variety of zero-sum con- tinuous state stochastic games.
Keywords:
Pages: 390-399
PS Link:
PDF Link: /papers/14/p390-kinathil.pdf
BibTex:
@INPROCEEDINGS{Kinathil14,
AUTHOR = "Shamin Kinathil and Scott Sanner and Nicolas Della Penna",
TITLE = "Closed-form Solutions to a Subclass of Continuous Stochastic Games via Symbolic Dynamic Programming",
BOOKTITLE = "Proceedings of the Thirtieth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-14)",
PUBLISHER = "AUAI Press",
ADDRESS = "Corvallis, Oregon",
YEAR = "2014",
PAGES = "390--399"
}


hosted by DSL   •   site info   •   help