2021/11/06 by Donsuk Lee, Lee, Donsuk, Samantha M. W. Wood +3 · 13 citations
Computer Science · Neuroscience · Psychology · #Animal behavior #Artificial Intelligence (cs.AI) #Artificial intelligence #Child and Animal Learning Development #Cognitive psychology #Cognitive science #Collective behavior #Computer science #Cooperative learning #Curiosity #FOS: Computer and information sciences #Natural (archaeology) #Neural dynamics and brain function #Psychology #Reinforcement Learning in Robotics #Reinforcement learning #Social learning #Social psychology #Sociology #Teaching method #cs.AI
paper · pdf · doi:10.48550/arxiv.2111.03796
published in arXiv (Cornell University) (Cornell University)
arxiv created 2021/11/06 · openalex publication_date 2021/11/06 · arxiv updated 2021/11/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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.