Efficient Inverse Multiagent Learning
This work addresses the challenge of inferring game parameters from observed behaviors in multiagent systems, with applications in domains like electricity markets, though it appears incremental as it builds on existing inverse game theory concepts.
The paper tackles the problem of inverse game theory and inverse multiagent learning by developing polynomial-time algorithms to find game parameters that yield observed equilibria, and it shows that this approach outperforms ARIMA in predicting Spanish electricity market prices.
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.