The operator approach to entropy games

10 Apr 2019  ·  Akian Marianne, Gaubert Stéphane, Grand-Clément Julien, Guillaud Jérémie ·

Entropy games and matrix multiplication games have been recently introduced by Asarin et al. They model the situation in which one player (Despot) wishes to minimize the growth rate of a matrix product, whereas the other player (Tribune) wishes to maximize it. We develop an operator approach to entropy games. This allows us to show that entropy games can be cast as stochastic mean payoff games in which some action spaces are simplices and payments are given by a relative entropy (Kullback-Leibler divergence). In this way, we show that entropy games with a fixed number of states belonging to Despot can be solved in polynomial time. This approach also allows us to solve these games by a policy iteration algorithm, which we compare with the spectral simplex algorithm developed by Protasov.

PDF Abstract
No code implementations yet. Submit your code now

Categories


Computer Science and Game Theory Optimization and Control

Datasets


  Add Datasets introduced or used in this paper