Efficient Regret Minimization in Non-Convex Games

Abstract

We consider regret minimization in repeated games with non-convex loss functions. Minimizing the standard notion of regret is computationally intractable. Thus, we define a natural notion of regret which permits efficient optimization and generalizes offline guarantees for convergence to an approximate local optimum. We give gradient-based methods that achieve optimal regret, which in turn guarantee convergence to equilibrium in this framework.

Published as a conference paper at ICML 2017

References in corpus (1)

• Connecting Generative Adversarial Networks and Actor-Critic Methods

Cited by in corpus (2)

• GANGs: Generative Adversarial Network Games
• Time-Smoothed Gradients for Online Forecasting