A Generalised Method for Empirical Game Theoretic Analysis

03/16/2018
by   Karl Tuyls, et al.
0

This paper provides theoretical bounds for empirical game theoretical analysis of complex multi-agent interactions. We provide insights in the empirical meta game showing that a Nash equilibrium of the meta-game is an approximate Nash equilibrium of the true underlying game. We investigate and show how many data samples are required to obtain a close enough approximation of the underlying game. Additionally, we extend the meta-game analysis methodology to asymmetric games. The state-of-the-art has only considered empirical games in which agents have access to the same strategy sets and the payoff structure is symmetric, implying that agents are interchangeable. Finally, we carry out an empirical illustration of the generalised method in several domains, illustrating the theory and evolutionary dynamics of several versions of the AlphaGo algorithm (symmetric), the dynamics of the Colonel Blotto game played by human players on Facebook (symmetric), and an example of a meta-game in Leduc Poker (asymmetric), generated by the PSRO multi-agent learning algorithm.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/14/2017

Symmetric Decomposition of Asymmetric Games

We introduce new theoretical insights into two-population asymmetric gam...
research
03/04/2019

α-Rank: Multi-Agent Evaluation by Evolution

We introduce α-Rank, a principled evolutionary dynamics methodology, for...
research
06/22/2022

Evolutionary Game-Theoretical Analysis for General Multiplayer Asymmetric Games

Evolutionary game theory has been a successful tool to combine classical...
research
06/13/2012

Identifying reasoning patterns in games

We present an algorithm that identifies the reasoning patterns of agents...
research
07/14/2023

Equilibrium Analysis of Customer Attraction Games

We introduce a game model called "customer attraction game" to demonstra...
research
01/22/2021

Estimating α-Rank by Maximizing Information Gain

Game theory has been increasingly applied in settings where the game is ...
research
03/08/2018

SA-IGA: A Multiagent Reinforcement Learning Method Towards Socially Optimal Outcomes

In multiagent environments, the capability of learning is important for ...

Please sign up or login with your details

Forgot password? Click here to reset