A Deep Reinforcement Learning Framework for Closed-loop Guidance of Fish Schools via Virtual Agents

2026-03-30 · Takato Shibayama, Hiroaki Kawashima arxiv

Guiding collective motion in biological groups is a fundamental challenge in understanding social interaction rules. In this study, we propose a deep reinforcement learning (RL) framework for closed-loop guidance of fish schools using virtual agents. These agents are controlled by policies trained via Proximal Policy Optimization (PPO) in simulation and deployed in physical experiments with rummy-nose tetras (Petitella bleheri), enabling real-time interaction between artificial agents and live individuals. To cope with the stochastic behavior of live individuals, we designed a composite reward function that balances directional guidance with cohesion, providing a form of functional biomimicry at the level of the control objective. Our systematic evaluation of visual parameters showed that a white background and larger stimulus sizes produced the highest guidance efficacy among the tested conditions in physical trials. Furthermore, evaluation across group sizes and agent configurations indicated that guidance efficacy decreased as the group size increased from five to eight individuals, and that using multiple independently controlled agents did not improve guidance. Analysis of agent motion in the physical trials indicated that, under the learned policy, the agent moved toward the target while remaining close to the school and re-approached the school after advancing too far ahead. This study highlights the potential of deep RL for closed-loop guidance of fish schools and identifies challenges in maintaining artificial influence in larger groups.

📄 PDF Abstract BibTeX arXiv:2603.28200

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Robots that learn to evaluate models of collective behavior

2026-04-08 · Mathis Hocke, Andreas Gerken, David Bierbach, Jens Krause 외 arxiv

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 comparis…

Reinforcement Learning for Low-Thrust Trajectory Design of Interplanetary Missions

2020-08-19 · Alessandro Zavoli, Lorenzo Federici

This paper investigates the use of Reinforcement Learning for the robust design of low-thrust interplanetary trajectories in presence of severe disturbances, modeled alternatively as Gaussian additive process noise, obse…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Robust Design+2

RoaD: Rollouts as Demonstrations for Closed-Loop Supervised Fine-Tuning of Autonomous Driving Policies

2025-12-01 · Guillermo Garcia-Cobo, Maximilian Igl, Peter Karkus, Zhejun Zhang 외 arxiv

Autonomous driving policies are typically trained via open-loop behavior cloning of human demonstrations. However, such policies suffer from covariate shift when deployed in closed loop, leading to compounding errors. We…

Reinforcement Learning Autonomous Driving

Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstration

2026-06-22 · Xinghao Zhu, Zixi Liu, Shalin Jain, Chenran Li 외 arxiv

Dexterous robot manipulation can benefit from the abundance of human demonstrations, but transferring such demonstrations to robot policies remains challenging. We present Contact Wrench Guidance from Human Demonstration…

Reinforcement Learning Robot Manipulation

Fisher Information Approach for Masking the Sensing Plan: Applications in Multifunction Radars

2024-03-24 · Shashwat Jain, Vikram Krishnamurthy, Muralidhar Rangaswamy, Bosung Kang 외

How to design a Markov Decision Process (MDP) based radar controller that makes small sacrifices in performance to mask its sensing plan from an adversary? The radar controller purposefully minimizes the Fisher informati…