Factored Reinforcement Learning (frl) is a new technique to solve Factored Markov Decision Problems (fmdps) when the structure of the problem is not known in advance. Like Anticipa...
Olivier Sigaud, Martin V. Butz, Olga Kozlova, Chri...
Recently, several learning algorithms relying on models with deep architectures have been proposed. Though they have demonstrated impressive performance, to date, they have only b...
Hugo Larochelle, Dumitru Erhan, Aaron C. Courville...
A number of representation schemes have been presented for use within Learning Classifier Systems, ranging from binary encodings to neural networks. This paper presents results fr...
—This paper details a learning decision-theoretic intelligent agent designed to solve the problem of guiding vehicles in the context of Personal Rapid Transit (PRT). The intellig...
Abstract. We study the problem of learning partitions using equivalence constraints as input. This is a binary classification problem in the product space of pairs of datapoints. ...