Controlling Fish Schools via Reinforcement Learning of Virtual Fish Movement
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917349904351232 |
|---|---|
| author | Nishii, Yusuke Kawashima, Hiroaki |
| author_facet | Nishii, Yusuke Kawashima, Hiroaki |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16384 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Controlling Fish Schools via Reinforcement Learning of Virtual Fish Movement Nishii, Yusuke Kawashima, Hiroaki Robotics Machine Learning Populations and Evolution 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. |
| title | Controlling Fish Schools via Reinforcement Learning of Virtual Fish Movement |
| topic | Robotics Machine Learning Populations and Evolution |
| url | https://arxiv.org/abs/2603.16384 |