Equilibrium Finding in Normal-Form Games via Greedy Regret Minimization
DOI:
https://doi.org/10.1609/aaai.v36i9.21181Keywords:
Multiagent Systems (MAS), Game Theory And Economic Paradigms (GTEP), Machine Learning (ML)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.Downloads
Published
2022-06-28
How to Cite
Zhang, H., Lerer, A., & Brown, N. (2022). Equilibrium Finding in Normal-Form Games via Greedy Regret Minimization. Proceedings of the AAAI Conference on Artificial Intelligence, 36(9), 9484-9492. https://doi.org/10.1609/aaai.v36i9.21181
Issue
Section
AAAI Technical Track on Multiagent Systems