Log In Sign Up

Meta-Learning in Games

by   Keegan Harris, et al.

In the literature on game-theoretic equilibrium finding, focus has mainly been on solving a single game in isolation. In practice, however, strategic interactions – ranging from routing problems to online advertising auctions – evolve dynamically, thereby leading to many similar games to be solved. To address this gap, we introduce meta-learning for equilibrium finding and learning to play games. We establish the first meta-learning guarantees for a variety of fundamental and well-studied classes of games, including two-player zero-sum games, general-sum games, and Stackelberg games. In particular, we obtain rates of convergence to different game-theoretic equilibria that depend on natural notions of similarity between the sequence of games encountered, while at the same time recovering the known single-game guarantees when the sequence of games is arbitrary. Along the way, we prove a number of new results in the single-game regime through a simple and unified framework, which may be of independent interest. Finally, we evaluate our meta-learning algorithms on endgames faced by the poker agent Libratus against top human professionals. The experiments show that games with varying stack sizes can be solved significantly faster using our meta-learning techniques than by solving them separately, often by an order of magnitude.


page 1

page 2

page 3

page 4


How and Why to Manipulate Your Own Agent

We consider strategic settings where several users engage in a repeated ...

Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers

Two-player, constant-sum games are well studied in the literature, but t...

Fictitious Play in Markov Games with Single Controller

Certain but important classes of strategic-form games, including zero-su...

A Generalized Training Approach for Multiagent Learning

This paper investigates a population-based training regime based on game...

Meta Arcade: A Configurable Environment Suite for Meta-Learning

Most approaches to deep reinforcement learning (DRL) attempt to solve a ...

No-Regret Learning in Games is Turing Complete

Games are natural models for multi-agent machine learning settings, such...

Multiagent Evaluation under Incomplete Information

This paper investigates the evaluation of learned multiagent strategies ...