EvoQRE: Modeling Bounded Rationality in Safety-Critical Traffic Simulation via Evolutionary Quantal Response Equilibrium

TL;DR

EvoQRE introduces a novel framework for modeling human-like bounded rationality in autonomous vehicle traffic simulations, improving realism and safety in safety-critical scenarios.

Contribution

It combines QRE with evolutionary dynamics in a new way, extending to continuous actions and providing theoretical convergence guarantees.

Findings

Achieves state-of-the-art realism in traffic simulation.

Improves safety metrics on benchmark datasets.

Enables controllable scenario generation via rationality parameters.

Abstract

Existing traffic simulation frameworks for autonomous vehicles typically rely on imitation learning or game-theoretic approaches that solve for Nash or coarse correlated equilibria, implicitly assuming perfectly rational agents. However, human drivers exhibit bounded rationality, making approximately optimal decisions under cognitive and perceptual constraints. We propose EvoQRE, a principled framework for modeling safety-critical traffic interactions as general-sum Markov games solved via Quantal Response Equilibrium (QRE) and evolutionary game dynamics. EvoQRE integrates a pre-trained generative world model with entropy-regularized replicator dynamics, capturing stochastic human behavior while maintaining equilibrium structure. We provide rigorous theoretical results, proving that the proposed dynamics converge to Logit-QRE under a two-timescale stochastic approximation with an explicit convergence rate of O(log k / k^{1/3}) under weak monotonicity assumptions. We further extend QRE to continuous action spaces using mixture-based and energy-based policy representations. Experiments on the Waymo Open Motion Dataset and nuPlan benchmark demonstrate that EvoQRE achieves state-of-the-art realism, improved safety metrics, and controllable generation of diverse safety-critical scenarios through interpretable rationality parameters.