Development of collective behavior in newborn artificial agents
This work addresses the foundational gap in understanding the developmental mechanisms of collective behavior for researchers in AI, psychology, and neuroscience, though it is incremental as it applies existing learning methods to a new domain.
The researchers tackled the problem of how collective behavior develops in newborn animals by using deep reinforcement learning and curiosity-driven learning to create artificial agents that learn from raw sensory inputs without external rewards. The agents spontaneously developed ego-motion, object recognition, and a preference for groupmates, rapidly acquiring core skills for collective behavior.
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.