Development of collective behavior in newborn artificial agents

Abstract

Collective behavior is widespread across the animal kingdom. To date, however, the developmental and mechanistic foundations of collective behavior have not been formally established. What learning mechanisms drive the development of collective behavior in newborn animals? Here, we used deep reinforcement learning and curiosity-driven learning -- two learning mechanisms deeply rooted in psychological and neuroscientific research -- to build newborn artificial agents that develop collective behavior. Like newborn animals, our agents learn collective behavior from raw sensory inputs in naturalistic environments. Our agents also learn collective behavior without external rewards, using only intrinsic motivation (curiosity) to drive learning. Specifically, when we raise our artificial agents in natural visual environments with groupmates, the agents spontaneously develop ego-motion, object recognition, and a preference for groupmates, rapidly learning all of the core skills required for collective behavior. This work bridges the divide between high-dimensional sensory inputs and collective action, resulting in a pixels-to-actions model of collective animal behavior. More generally, we show that two generic learning mechanisms -- deep reinforcement learning and curiosity-driven learning -- are sufficient to learn collective behavior from unsupervised natural experience.

References in corpus (13)

• Novel type of phase transition in a system of self-driven particles
• Interaction Ruling Animal Collective Behaviour Depends on Topological rather than Metric Distance: Evidence from a Field Study
• How simple rules determine pedestrian behavior and crowd disasters
• Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
• Emergence of Locomotion Behaviours in Rich Environments
• Unity: A General Platform for Intelligent Agents
• Collective Motion of Moshers at Heavy Metal Concerts
• Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learner
• The Role of Projection in the Control of Bird Flocks
• Zebrafish collective behaviour in heterogeneous environment modeled by a stochastic model based on visual perception
• Flocking in complex environments -- attention trade-offs in collective information processing
• Intrinsically motivated collective motion
• Modelling collective motion based on the principle of agency