用强化学习模拟电鱼集体觅食，揭示社会行为的神经机制。
Active Electrosensing and Communication in MARL-trained Weakly Electric Fish Collectives
- 用MARL训练仿生电鱼模型，实现主动感应与社交觅食。
- 模型重现真实电鱼的轨迹与放电模式，展现支配与攻击行为。
- 通过虚拟干预验证感知与社交对觅食的关键作用。
复杂群体行为如何从个体互动中涌现，是基础科学的核心问题，但动物实验成本高且难以同步多脑记录，限制了直接研究。本文提出一种新型计算框架，模拟具有生物物理启发电感应与动作能力的类电鱼智能体，通过多智能体强化学习（MARL）训练其集体觅食。训练后的智能体再现真实电鱼的特征，包括曲线归巢轨迹和重尾电器官放电（EOD）间隔分布，同时表现出主动感知、社会觅食、类似支配的不对称性及攻击行为。通过传感器切除、沉默放电和食物分布变化等在仿真中干预，识别出社会觅食的因果驱动因素。对循环神经网络动态的分析进一步显示任务相关变量和社会情境的稳健编码。该工作对弱电鱼及其他难以进行大规模多个体神经记录的社会动物的神经行为学研究具有广泛意义。
原文摘要 · Abstract (English)
How complex collective behavior emerges from individual interactions is a fundamental scientific question, but experimental cost and difficulty of simultaneous multi-brain recordings limit direct study in animals. Here we introduce a novel computational framework modeling weakly electric fish-like agents with biophysically inspired electrosensing and actuation, trained to forage collectively via multi-agent reinforcement learning (MARL). Trained agents reproduce hallmarks of real fish, including curvilinear homing trajectories and heavy-tailed electric organ discharge (EOD) interval statistics, while exhibiting emergent active sensing, social foraging, dominance-like asymmetries, and aggression. We perform in silico interventions including sensor ablations, EOD silencing, and food distribution changes to identify causal drivers of social foraging. Analyses of recurrent neural dynamics further show robust encoding of task-relevant variables and social context. Our work has broad implications for the neuroethology of weakly electric fish and other social animals where extensive multi-individual neural recordings, and thus traditional data-driven modeling, remain challenging.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。