— We consider the problem of optimal control in continuous and partially observable environments when the parameters of the model are not known exactly. Partially Observable Mark...
This paper describes a novel real-world reinforcement learning application: The Neuro Slot Car Racer. In addition to presenting the system and first results based on Neural Fitted...
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
Abstract. Feature selection in reinforcement learning (RL), i.e. choosing basis functions such that useful approximations of the unkown value function can be obtained, is one of th...
To avoid the curse of dimensionality, function approximators are used in reinforcement learning to learn value functions for individual states. In order to make better use of comp...