You are currently offline. Some features of the site may not work correctly.

Corpus ID: 219558780

Stochastic matrix games with bandit feedback

@article{ODonoghue2020StochasticMG,
title={Stochastic matrix games with bandit feedback},
author={Brendan O'Donoghue and Tor Lattimore and Ian Osband},
journal={ArXiv},
year={2020},
volume={abs/2006.05145}
}

We study a version of the classical zero-sum matrix game with unknown payoff matrix and bandit feedback, where the players only observe each others actions and a noisy payoff. This generalizes the usual matrix game, where the payoff matrix is known to the players. Despite numerous applications, this problem has received relatively little attention. Although adversarial bandit algorithms achieve low regret, they do not exploit the matrix structure and perform poorly relative to the new… Expand