Controlling Fish Schools via Reinforcement Learning of Virtual Fish Movement

TL;DR

This paper demonstrates that reinforcement learning can be used to control and guide fish schools using virtual fish, successfully influencing real fish behavior in experiments and outperforming baseline strategies.

Contribution

It introduces a model-free reinforcement learning approach to guide real fish using virtual agents, overcoming physical constraints and behavioral modeling challenges.

Findings

Reinforcement learning policies effectively guide fish schools in simulation.

Real-world experiments show successful guidance of fish towards targets.

The method significantly outperforms baseline and heuristic strategies.

Abstract

This study investigates a method to guide and control fish schools using virtual fish trained with reinforcement learning. We utilize 2D virtual fish displayed on a screen to overcome technical challenges such as durability and movement constraints inherent in physical robotic agents. To address the lack of detailed behavioral models for real fish, we adopt a model-free reinforcement learning approach. First, simulation results show that reinforcement learning can acquire effective movement policies even when simulated real fish frequently ignore the virtual stimulus. Second, real-world experiments with live fish confirm that the learned policy successfully guides fish schools toward specified target directions. Statistical analysis reveals that the proposed method significantly outperforms baseline conditions, including the absence of stimulus and a heuristic "stay-at-edge" strategy. This study provides an early demonstration of how reinforcement learning can be used to influence collective animal behavior through artificial agents.