This paper studies the rationality of an individual player in sequential games of perfect information played with other players who are not necessarily rational. The paper proposes a set of properties on the choice behavior and shows that they are equivalent to the rationality of an individual player at the initial node independently of the behavioral norm of the other players. Furthermore, I s...

In this invited paper, we study the concept of admissible strategies for two player win/lose infinite sequential games with imperfect information. We show that in stark contrast with the perfect information variant, admissible strategies are only guaranteed to exist when players have objectives that are closed sets. As a consequence, we also study decision problems related to the existence of a...

We consider Gillette’s two-person zero-sum stochastic games with perfect information. For each k ∈ Z+ we introduce a payoff function, called the k-total reward. For k = 0 and 1 these payoffs are known as mean payoff and total reward, respectively. We restrict our attention to the deterministic case, the so called cyclic games. For all k, we prove the existence of a saddle point which can be rea...

function is a function which estimates what resulting value Two-person, perfect information, constant sum games have been studied in Artificial Intelligence. This paper opens up the issue of playing n-person games and proposes a procedure for constant sum or non-constant sum games. It is proved that a procedure, max”, locates an equilibrium point given the entire game tree. The minimax procedur...

Alternating-time Temporal Logic (ATL∗) is a central logic for multiagent systems. Its extension to the imperfect information setting (ATLi ) is well known to have an undecidable model-checking problem when agents have perfect recall. Studies have thus mostly focused either on agents without memory, or on alternative semantics to retrieve decidability. In this work we establish new decidability ...

The theory of incomplete contracts has been recently questioned using or extending the subgame perfect implementation approach of Moore and Repullo (1988). We consider the robustness of this mechanism to the introduction of small amounts of asymmetric information. Our main result is that the mechanism may not yield (even approximately) truthful revelation as the amount of asymmetric information...

Deep Learning has become most popular research topic because of its ability to learn from a huge amount of data. In recent research such as Atari 2600 games, they show that Deep Convolutional Neural Network (Deep CNN) can learn abstract information from pixel 2D data. After that, in VizDoom, we can also see the effect of pixel 3D data in learning to play games. But in all the cases above, the g...

We give a policy-improvement type algorithm to locate an optimal pure stationary strategy for discounted stochastic games with perfect information. A graph theoretic motivation for our algorithm is presented as well.