Search based planners such as A* and Dijkstra's algorithm are proven methods for guiding today's robotic systems. Although such planners are typically based upon a coarse approximation of reality, they are nonetheless valuable due to their ability to reason about the future, and to generalize to previously unseen scenarios. However, encoding the desired behavior of a system into the underlying cost function used by the planner can be a tedious and error-prone task. We introduce Reinforcement Planning, which extends gradient based reinforcement learning algorithms to automatically learn useful surrogate cost functions for optimal planners. Reinforcement Planning presents several advantages over other learning approaches to planning in that it is not limited by the expertise of a human demonstrator, and that it acknowledges the domain of the planner is a simplified model of the world. We demonstrate the effectiveness of our method in learning to solve a noisy physical simulation of the well-known “marble maze” toy.