Meta-Learning in Games

09/28/2022
by   Keegan Harris, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/26/2023

On the Convergence of No-Regret Learning Dynamics in Time-Varying Games

Most of the literature on learning in games has focused on the restricti...
research
12/14/2021

How and Why to Manipulate Your Own Agent

We consider strategic settings where several users engage in a repeated ...
research
06/17/2021

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

Two-player, constant-sum games are well studied in the literature, but t...
research
09/27/2019

A Generalized Training Approach for Multiagent Learning

This paper investigates a population-based training regime based on game...
research
12/01/2021

Meta Arcade: A Configurable Environment Suite for Meta-Learning

Most approaches to deep reinforcement learning (DRL) attempt to solve a ...
research
02/24/2022

No-Regret Learning in Games is Turing Complete

Games are natural models for multi-agent machine learning settings, such...
research
09/21/2019

Multiagent Evaluation under Incomplete Information

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

Please sign up or login with your details

Forgot password? Click here to reset