Understanding Electro-communication and Electro-sensing in Weakly Electric Fish using Multi-Agent Deep Reinforcement Learning

2025-11-11

AI Summary

Addressing the experimental challenges in studying weakly electric fish electrosensory perception and electrocommunication, this work proposes a multi-agent deep reinforcement learning framework based on recurrent neural networks, modeling electric signal emission, propagation, and cross-individual perception within a virtual aquatic environment. Inspired by evolutionary principles, we introduce an individual fitness-based reward—without explicit social rewards—to drive emergent, biologically plausible collective behaviors, including cooperative foraging and parasitic discharging. The model successfully reproduces key empirical features of real weakly electric fish: heavy-tailed inter-discharge intervals, environment-dependent discharge modulation, conspecific signal preference, and dominance effects on foraging efficiency. Crucially, it reveals, for the first time, how competitive pressure and environmental feedback jointly shape electrocommunication dynamics through social mechanisms. This provides an interpretable computational paradigm for understanding the evolution and collective intelligence of active electrosensory systems. (149 words)

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Machine Learning: Evolutionary Learning

Application Category

• Economics, Online Markets and Human Computation: Social networks and social learning
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Weakly electric fish, like Gnathonemus petersii, use a remarkable electrical modality for active sensing and communication, but studying their rich electrosensing and electrocommunication behavior and associated neural activity in naturalistic settings remains experimentally challenging. Here, we present a novel biologically-inspired computational framework to study these behaviors, where recurrent neural network (RNN) based artificial agents trained via multi-agent reinforcement learning (MARL) learn to modulate their electric organ discharges (EODs) and movement patterns to collectively forage in virtual environments. Trained agents demonstrate several emergent features consistent with real fish collectives, including heavy tailed EOD interval distributions, environmental context dependent shifts in EOD interval distributions, and social interaction patterns like freeloading, where agents reduce their EOD rates while benefiting from neighboring agents'active sensing. A minimal two-fish assay further isolates the role of electro-communication, showing that access to conspecific EODs and relative dominance jointly shape foraging success. Notably, these behaviors emerge through evolution-inspired rewards for individual fitness and emergent inter-agent interactions, rather than through rewarding agents explicitly for social interactions. Our work has broad implications for the neuroethology of weakly electric fish, as well as other social, communicating animals in which extensive recordings from multiple individuals, and thus traditional data-driven modeling, are infeasible.

Problem

• Studying weakly electric fish electrosensing and communication in naturalistic settings
• Developing multi-agent reinforcement learning to model collective foraging behaviors
• Investigating emergent electro-communication patterns without explicit social rewards

Innovation

• Multi-agent reinforcement learning trains RNN-based agents
• Agents modulate electric discharges and movement patterns
• Evolution-inspired rewards shape emergent social interactions