# Equilibrium Finding in Normal-Form Games Via Greedy Regret Minimization

arXiv: https://arxiv.org/abs/2204.04826 · HTML: https://mlsanity.com/paper/2204.04826/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2022.

## Built on by (most cited first, 5 of 5)

- [A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games](https://mlsanity.com/paper/2206.05825/) (2022)
- [A Survey of Decision Making in Adversarial Games](https://mlsanity.com/paper/2207.07971/) (2022)
- [Efficient Last-iterate Convergence Algorithms in Solving Games](https://mlsanity.com/paper/2308.11256/) (2023)
- [Easy as ABCs: Unifying Boltzmann Q-Learning and Counterfactual Regret Minimization](https://mlsanity.com/paper/2402.11835/) (2024)
- [Barriers to Welfare Maximization with No-Regret Learning](https://mlsanity.com/paper/2411.01720/) (2024)

## Abstract (arXiv)

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.