Learning Parameterized Families of Games

02/25/2023
by   Madelyn Gatchel, et al.
0

Nearly all simulation-based games have environment parameters that affect incentives in the interaction but are not explicitly incorporated into the game model. To understand the impact of these parameters on strategic incentives, typical game-theoretic analysis involves selecting a small set of representative values, and constructing and analyzing separate game models for each value. We introduce a novel technique to learn a single model representing a family of closely related games that differ in the number of symmetric players or other ordinal environment parameters. Prior work trains a multi-headed neural network to output mixed-strategy deviation payoffs, which can be used to compute symmetric ε-Nash equilibria. We extend this work by making environment parameters into input dimensions of the regressor, enabling a single model to learn patterns which generalize across the parameter space. For continuous and discrete parameters, our results show that these generalized models outperform existing approaches, achieving better accuracy with far less data. This technique makes thorough analysis of the parameter space more tractable, and promotes analyses that capture relationships between parameters and incentives.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/26/2023

Data Structures for Deviation Payoffs

We present new data structures for representing symmetric normal-form ga...
research
04/22/2021

Nash Equilibria of The Multiplayer Colonel Blotto Game on Arbitrary Measure Spaces

The Colonel Blotto Problem proposed by Borel in 1921 has served as a wid...
research
08/12/2022

Computational and Data Requirements for Learning Generic Properties of Simulation-Based Games

Empirical game-theoretic analysis (EGTA) is primarily focused on learnin...
research
01/13/2023

Bridging the Gap Between Single and Multi Objective Games

A classic model to study strategic decision making in multi-agent system...
research
11/30/2022

Regret Pruning for Learning Equilibria in Simulation-Based Games

In recent years, empirical game-theoretic analysis (EGTA) has emerged as...
research
10/05/2022

Atari-5: Distilling the Arcade Learning Environment down to Five Games

The Arcade Learning Environment (ALE) has become an essential benchmark ...
research
05/28/2015

Multidefender Security Games

Stackelberg security game models and associated computational tools have...

Please sign up or login with your details

Forgot password? Click here to reset