Proceedings:
No. 9: AAAI-22 Technical Tracks 9
Volume
Issue:
Proceedings of the AAAI Conference on Artificial Intelligence, 36
Track:
AAAI Technical Track on Multiagent Systems
Downloads:
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.
DOI:
10.1609/aaai.v36i9.21181
AAAI
Proceedings of the AAAI Conference on Artificial Intelligence, 36