Turbocharging Solution Concepts: Solving NEs, CEs and CCEs with Neural Equilibrium Solvers
This provides a faster and more reliable component for multiagent machine learning algorithms, though it is incremental as it builds on existing equilibrium concepts with a new computational method.
The paper tackles the problem of solving normal-form games for equilibria like Nash, Correlated, and Coarse Correlated Equilibria, which are slow and non-deterministic, by introducing a Neural Equilibrium Solver that uses an equivariant neural network to approximate solutions quickly and deterministically, achieving zero-shot generalization to larger games.
Solution concepts such as Nash Equilibria, Correlated Equilibria, and Coarse Correlated Equilibria are useful components for many multiagent machine learning algorithms. Unfortunately, solving a normal-form game could take prohibitive or non-deterministic time to converge, and could fail. We introduce the Neural Equilibrium Solver which utilizes a special equivariant neural network architecture to approximately solve the space of all games of fixed shape, buying speed and determinism. We define a flexible equilibrium selection framework, that is capable of uniquely selecting an equilibrium that minimizes relative entropy, or maximizes welfare. The network is trained without needing to generate any supervised training data. We show remarkable zero-shot generalization to larger games. We argue that such a network is a powerful component for many possible multiagent algorithms.