Abstract. We investigate the problem of using function approximation in reinforcement learning where the agent’s policy is represented as a classifier mapping states to actions....
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...
CBR is one of the techniques that can be applied to the task of approximating a function over high-dimensional, continuous spaces. In Reinforcement Learning systems a learning agen...
We propose a model-based learning algorithm, the Adaptive Aggregation Algorithm (AAA), that aims to solve the online, continuous state space reinforcement learning problem in a de...
Given the growing complexity of tasks that spoken dialogue systems are trying to handle, Reinforcement Learning (RL) has been increasingly used as a way of automatically learning ...