Mehrdad Valizadeh | Searcharxiv

arXiv2019

Playing Games with Bounded Entropy: Convergence Rate and Approximate Equilibria

We consider zero-sum repeated games in which the players are restricted to strategies that require only a limited amount of randomness. Let $v_n$ be the max-min value of the $n$ stage game; previous works have characterized $\lim_{n\rightarrow\infty}v_n$, i.e., the long-run max-min value. Our first contribution is to study the convergence rate of $v_n$ to its limit. To this end, we provide a new tool for simulation of a source (target source) from another source (coin source). Considering the total variation distance as the measure of precision, this tool offers an upper bound for the precision of simulation, which is vanishing exponentially in the difference of Rényi entropies of the coin and target sources. In the second part of paper, we characterize the set of all approximate Nash equilibria achieved in long run. It turns out that this set is in close relation with the long-run max-min value.

cs.GT↗

arXiv2018

Playing Games with Bounded Entropy

In this paper, we consider zero-sum repeated games in which the maximizer is restricted to strategies requiring no more than a limited amount of randomness. Particularly, we analyze the maxmin payoff of the maximizer in two models: the first model forces the maximizer to randomize her action in each stage just by conditioning her decision to outcomes of a given sequence of random source, whereas, in the second model, the maximizer is a team of players who are free to privately randomize their corresponding actions but do not have access to any explicit source of shared randomness needed for cooperation. The works of Gossner and Vieille, and Gossner and Tomala adopted the method of types to establish their results; however, we utilize the idea of random hashing which is the core of randomness extractors in the information theory literature. In addition, we adopt the well-studied tool of simulation of a source from another source. By utilizing these tools, we are able to simplify the prior results and generalize them as well. We characterize the maxmin payoff of the maximizer in the repeated games under study. Particularly, the maxmin payoff of the first model is fully described by the function $J(h)$ which is the maximum payoff that the maximizer can secure in a one-shot game by choosing mixed strategies of entropy at most $h$. In the second part of the paper, we study the computational aspects of $J(h)$. We offer three explicit lower bounds on the entropy-payoff trade-off curve. To do this, we provide and utilize new results for the set of distributions that guarantee a certain payoff for Alice. In particular, we study how this set of distributions shrinks as we increase the security level. While the use of total variation distance is common in game theory, our derivation indicates the suitability of utilizing the Renyi-divergence of order two.

cs.IT↗