Inverse Learning in $2\times2$ Games: From Synthetic Interactions to Traffic Simulation
By: Daniela Aguirre Salazar, Firas Moatemri, Tatiana Tatarenko
Understanding how agents coordinate or compete from limited behavioral data is central to modeling strategic interactions in traffic, robotics, and other multi-agent systems. In this work, we investigate the following complementary formulations of inverse game-theoretic learning: (i) a Closed-form Correlated Equilibrium Maximum-Likelihood estimator (CE-ML) specialized for $2\times2$ games; and (ii) a Logit Best Response Maximum-Likelihood estimator (LBR-ML) that captures long-run adaptation dynamics via stochastic response processes. Together, these approaches span the spectrum between static equilibrium consistency and dynamic behavioral realism. We evaluate them on synthetic "chicken-dare" games and traffic-interaction scenarios simulated in SUMO, comparing parameter recovery and distributional fit. Results reveal clear trade-offs between interpretability, computational tractability, and behavioral expressiveness across models.
Similar Papers
Bayesian Inverse Games with High-Dimensional Multi-Modal Observations
Machine Learning (CS)
Learns what others want to help robots act safely.
What Do Agents Think Others Would Do? Level-2 Inverse Games for Inferring Agents' Estimates of Others' Objectives
CS and Game Theory
Helps robots understand what others think.
Efficient Inverse Multiagent Learning
CS and Game Theory
Helps predict electricity prices better than old ways.