Tractable Local Equilibria in Non-Concave Games

arXiv:2403.08171v1 Announce Type: cross
Abstract: While Online Gradient Descent and other no-regret learning procedures are known to efficiently converge to coarse correlated equilibrium in games where each agent's utility is concave in their own strategy, this is not the case when the utilities are non-concave, a situation that is common in machine learning applications where the agents' strategies are parameterized by deep neural networks, or the agents' utilities are computed by a neural network, or both. Indeed, non-concave games present …

abstract agent applications arxiv case converge cs.gt cs.lg equilibria equilibrium games gradient machine machine learning machine learning applications strategy tractable type utilities utility