Universal Notice Networks: Transferring Learned Skills Through a Broad Panel of Applications

Despite great achievements of reinforcement learning based works, those methods are known for their poor sample efficiency. This particular drawback usually means training agents in simulated environments is the only viable option, regarding time constraints. Furthermore, reinforcement learning agents have a strong tendency to overfit on their environment, observing a drastic loss of performances at test time. As a result, tying the agent logic to its current body may very well make transfer unefficient. To tackle that issue, we propose the Universal Notice Network (UNN) method to enforce separation of the neural network layers holding information to solve the task from those related to robot properties, hence enabling easier transfer of knowledge between entities. We demonstrate the efficiency of this method on a broad panel of applications, we consider different kinds of robots, with different morphological structures performing kinematic, dynamic single and multi-robot tasks. We prove that our method produces zero shot (without additionnal learning) transfers that may produce better performances than state-of-the art approaches and show that a fast tuning enhances those performances.