Efficient Inverse Multiagent Learning
Abstract
In this paper, we study inverse game theory (resp. inverse multiagent learning) in which the goal is to find parameters of a game's payoff functions for which the expected (resp. sampled) behavior is an equilibrium. We formulate these problems as generative-adversarial (i.e., min-max) optimization problems, for which we develop polynomial-time algorithms to solve, the former of which relies on an exact first-order oracle, and the latter, a stochastic one. We extend our approach to solve inverse multiagent simulacral learning in polynomial time and number of samples. In these problems, we seek a simulacrum, meaning parameters and an associated equilibrium that replicate the given observations in expectation. We find that our approach outperforms the widely-used ARIMA method in predicting prices in Spanish electricity markets based on time-series data.
Cite
@article{arxiv.2502.14160,
title = {Efficient Inverse Multiagent Learning},
author = {Denizalp Goktas and Amy Greenwald and Sadie Zhao and Alec Koppel and Sumitra Ganesh},
journal= {arXiv preprint arXiv:2502.14160},
year = {2025}
}
Comments
Paper was submitted to the International Conference on Learning Representations (2024) under the title of "Generative Adversarial Inverse Multiagent Learning", and renamed for the camera-ready submission as "Efficient Inverse Multiagent Learning"