Self-supervision unlocks depth scaling in reinforcement learning – and results in unanticipated exploratory behaviors

By Frederick d’Oleire Uquillas, Science Communications Fellow for the AI Lab For years, reinforcement learning has typically relied on relatively shallow neural network architectures. In language and vision, researchers increased depth to hundreds of layers and observed the emergence of new capabilities. In reinforcement learning (RL), by contrast, most architectures used two to five layers, […]