← Back to Benchmarks
simmediumroboticsmetric · varies

Robots that learn to evaluate models of collective behavior

Description

Understanding and modeling animal behavior is essential for studying collective motion, decision-making, and bio-inspired robotics. Yet, evaluating the accuracy of behavioral models still often relies on offline comparisons to static trajectory statistics. Here we introduce a reinforcement-learning-based framework that uses a biomimetic robotic fish (RoboFish) to evaluate computational models of live fish behavior through closed-loop interaction. We trained policies in simulation using four dist

Source

http://arxiv.org/abs/2604.07303v1