Equilibrium finding in normal-form games via greedy regret minimization
Proceedings of the AAAI Conference on Artificial Intelligence, 2022•ojs.aaai.org
We extend the classic regret minimization framework for approximating equilibria in normal-
form games by greedily weighing iterates based on regrets observed at runtime.
Theoretically, our method retains all previous convergence rate guarantees. Empirically,
experiments on large randomly generated games and normal-form subgames of the AI
benchmark Diplomacy show that greedy weights outperforms previous methods whenever
sampling is used, sometimes by several orders of magnitude.
form games by greedily weighing iterates based on regrets observed at runtime.
Theoretically, our method retains all previous convergence rate guarantees. Empirically,
experiments on large randomly generated games and normal-form subgames of the AI
benchmark Diplomacy show that greedy weights outperforms previous methods whenever
sampling is used, sometimes by several orders of magnitude.
Abstract
We extend the classic regret minimization framework for approximating equilibria in normal-form games by greedily weighing iterates based on regrets observed at runtime. Theoretically, our method retains all previous convergence rate guarantees. Empirically, experiments on large randomly generated games and normal-form subgames of the AI benchmark Diplomacy show that greedy weights outperforms previous methods whenever sampling is used, sometimes by several orders of magnitude.
ojs.aaai.org
Showing the best result for this search. See all results