Optimal Control with Natural Images: Efficient Reinforcement Learning using Overcomplete Sparse Codes

ArXi:2412.08893v3 Announce Type: replace-cross Optimal control and sequential decision making are widely used in many complex tasks. Optimal control over a sequence of natural images is a first step towards understanding the role of vision in control. Here, we formalize this problem as a reinforcement learning task, and derive general conditions under which an image includes enough information to implement an optimal policy.