Run the GAMUT: A Comprehensive Approach to Evaluating Game-Theoretic Algorithms

Abstract

We present GAMUT^1, a suite of game generators designed for testing game-theoretic algorithms. We explain why such a generator is necessary, offer a way of visualizing relationships between the sets of games supported by GAMUT, and give an overview of GAMUTýs architecture. We highlight the importance of using comprehensive test data by benchmarking existing algorithms. We show surprisingly large variation in algorithm performance across different sets of games for two widely-studied problems: computing Nash equilibria and multiagent learning in repeated games.

DOI: 10.1109/AAMAS.2004.238

Extracted Key Phrases

1 Figure or Table

01020'04'06'08'10'12'14'16
Citations per Year

170 Citations

Semantic Scholar estimates that this publication has 170 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Nudelman2004RunTG, title={Run the GAMUT: A Comprehensive Approach to Evaluating Game-Theoretic Algorithms}, author={Eugene Nudelman and Jennifer Wortman Vaughan and Yoav Shoham and Kevin Leyton-Brown}, booktitle={AAMAS}, year={2004} }