Efficient Inverse Multiagent Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Goktas, Denizalp, Greenwald, Amy, Zhao, Sadie, Koppel, Alec, Ganesh, Sumitra
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910835931086848
author Goktas, Denizalp
Greenwald, Amy
Zhao, Sadie
Koppel, Alec
Ganesh, Sumitra
author_facet Goktas, Denizalp
Greenwald, Amy
Zhao, Sadie
Koppel, Alec
Ganesh, Sumitra
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_14160
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient Inverse Multiagent Learning
Goktas, Denizalp
Greenwald, Amy
Zhao, Sadie
Koppel, Alec
Ganesh, Sumitra
Computer Science and Game Theory
Artificial Intelligence
Machine Learning
Theoretical Economics
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.
title Efficient Inverse Multiagent Learning
topic Computer Science and Game Theory
Artificial Intelligence
Machine Learning
Theoretical Economics
url https://arxiv.org/abs/2502.14160