Dissecting Larval Zebrafish Hunting using Deep Reinforcement Learning Trained RNN Agents

2025-10-04

AI Summary

This study investigates how ecological and energetic constraints shape adaptive predatory behavior in zebrafish larvae, and explores the generality of such principles across biological brains and artificial agents. Using a behavior-segment-based virtual zebrafish simulator, we trained recurrent neural networks (RNNs) via deep reinforcement learning—receiving only binocular visual input, motor-visual coupling, and moderate energy-cost penalties. The model spontaneously exhibited key ethologically relevant behaviors: vergence-based prey tracking, velocity modulation, and stereotyped approach trajectories. Critically, no biological neural data or fine-grained neuroanatomical details were incorporated. Our framework reveals an emergent optimal trade-off between sensory gain and metabolic cost, yielding testable neuroscientific predictions. Methodologically, we integrate parameter sweeps, quantitative trajectory analysis, and virtual ecological manipulation. This yields a parsimonious, cross-scale computational paradigm for understanding the principles underlying adaptive behavior.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Larval zebrafish hunting provides a tractable setting to study how ecological and energetic constraints shape adaptive behavior in both biological brains and artificial agents. Here we develop a minimal agent-based model, training recurrent policies with deep reinforcement learning in a bout-based zebrafish simulator. Despite its simplicity, the model reproduces hallmark hunting behaviors -- including eye vergence-linked pursuit, speed modulation, and stereotyped approach trajectories -- that closely match real larval zebrafish. Quantitative trajectory analyses show that pursuit bouts systematically reduce prey angle by roughly half before strike, consistent with measurements. Virtual experiments and parameter sweeps vary ecological and energetic constraints, bout kinematics (coupled vs. uncoupled turns and forward motion), and environmental factors such as food density, food speed, and vergence limits. These manipulations reveal how constraints and environments shape pursuit dynamics, strike success, and abort rates, yielding falsifiable predictions for neuroscience experiments. These sweeps identify a compact set of constraints -- binocular sensing, the coupling of forward speed and turning in bout kinematics, and modest energetic costs on locomotion and vergence -- that are sufficient for zebrafish-like hunting to emerge. Strikingly, these behaviors arise in minimal agents without detailed biomechanics, fluid dynamics, circuit realism, or imitation learning from real zebrafish data. Taken together, this work provides a normative account of zebrafish hunting as the optimal balance between energetic cost and sensory benefit, highlighting the trade-offs that structure vergence and trajectory dynamics. We establish a virtual lab that narrows the experimental search space and generates falsifiable predictions about behavior and neural coding.

Problem

• Modeling zebrafish hunting behavior using deep reinforcement learning
• Identifying ecological constraints enabling realistic pursuit dynamics
• Establishing virtual lab for neuroscience predictions and analysis

Innovation

• Trained recurrent policies with deep reinforcement learning
• Used minimal agent-based model in zebrafish simulator
• Identified compact constraints sufficient for hunting behavior