Games are used to evaluate and advance Multiagent and Artificial Intelligence techniques. Most of these games are deterministic with perfect information (e.g. Chess and Checkers). A deterministic game has no chance element and in a perfect information game, all information is visible to all players. However, many real-world scenarios with competing agents are stochastic (non-deterministic) with...

Function approximation (FA) has been a critical component in solving large zero-sum games. Yet, little attention given towards FA general-sum extensive-form games, despite them being widely regarded as computationally more challenging than their fully competitive or cooperative counterparts. A key challenge is that for many equilibria no simple analogue to the state value function used Markov D...

We address the problem of solving parity games with imperfect information on finite graphs of bounded structural complexity. It is a major open problem whether parity games with perfect information can be solved in Ptime. Restricting the structural complexity of the game arenas, however, often leads to efficient algorithms for parity games. Such results are known for graph classes of bounded tr...

Monte Carlo Tree Search (MCTS) is an AI technique that has been successfully applied to many deterministic games of perfect information, leading to large advances in a number of domains, such as Go and General Game Playing. Imperfect information games are less well studied in the field of AI despite being popular and of significant commercial interest, for example in the case of computer and mo...

We address the question of existence of equilibrium in general timing games with complete information. Under weak assumptions, any two-player timing game has a Markov subgame perfect e-equilibrium, for each e40: This result is tight. For some classes of games (symmetric games, games with cumulative payoffs), stronger existence results are established. r 2004 Elsevier Inc. All rights reserved. J...

We characterize strategy sets that are closed under rational behavior (curb) in extensive games of perfect information and finite horizon. It is shown that any such game possesses only one minimal curb set, which necessarily includes all its subgame perfect Nash equilibria. Applications of this result are twofold. First, it lessens computational burden while computing minimal curb sets. Second,...