Deep Learning Across Games

2024/09/23 by Condorelli, Daniele, Furlan, Massimiliano
#FOS: Economics and business #Theoretical Economics (econ.TH)

paper · doi:10.48550/arxiv.2409.15197

Abstract

We train two neural networks adversarially to play static games. At each iteration, a row and column network observe a new random bimatrix game and output individual mixed strategies. The parameters of each network are independently updated via stochastic gradient descent on a loss defined by the individual squared regret experienced in the game. Simulations show the joint behavior of the trained networks approximates a Nash equilibrium in all games. In 2×2 games with multiple equilibria, the networks select the risk dominant equilibrium. These findings, which are robust and generalise out-of-distribution, illustrate how equilibrium emerges from learning across heterogeneous games.

Related

• A Deep Learning Method for Optimal Investment Under Relative Performance Criteria Among Heterogeneous Agents
• Finding Mixed Nash Equilibria of Generative Adversarial Networks
• Achieving Correlated Equilibrium by Studying Opponent's Behavior Through\n Policy-Based Deep Reinforcement Learning
• Dynamic Game Theoretic Neural Optimizer
• Neural Population Learning beyond Symmetric Zero-sum Games