Abstract

We consider the complexity of stochastic games -- simple games of chance played by two players. We show that the problem of deciding which player has the greatest chance of winning the game is in the class NP " co-NP. 1 Introduction We consider the complexity of a natural combinatorial problem, that of deciding the outcome of a special kind of stochastic game. A simple stochastic game (SSG) is a directed graph with three types of vertices, called max, min and average vertices. There is a special start vertex and two special sink vertices, called the 0-sink and the 1-sink. For simplicity, we assume that all vertices have exactly two (not necessarily distinct) neighbors, except for the sink vertices, which have no neighbors. The graph models a game between two players, 0 and 1. In the game, a token is initially placed on the start vertex, and at each step of the game the token is moved from a vertex to one of its neighbors, according to the following rules: At a min vertex, player 0 cho...

Citations

433	Dynamic Programming and Markov Processes - Howard - 1960
306	A polynomial algorithm in linear programming, Doklady Akad - Khachiyan - 1979
210	Computational complexity of probabilistic Turing machines - Gill - 1977
159	Stochastic games - Shapley - 1953
90	Games against Nature, in - Papadimitriou - 1983
30	Finite state Markov decision processes - Derman - 1972
27	Computational Models of Games - Condon - 1989
9	Ordered field property for stochastic games when the player who controls transitions changes from state to state - Filar - 1981
5	Surveys in game theory and related topics, CWI Tract 39. Centrum voor Wiskunde en Informatica - Peters, Vrieze - 1987