Abstract. We present an implementation of model-based online reinforcement learning (RL) for continuous domains with deterministic transitions that is specifically designed to achi...
The standardization of the design of learning games is a contradictory topic: The existence of a rich variety of domains and applications is in conflict with the desire for unifica...
Sebastian Kelle, Roland Klemke, Marion R. Gruber, ...
Discriminative methods for visual object category recognition are typically non-probabilistic, predicting class labels but not directly providing an estimate of uncertainty. Gauss...
Ashish Kapoor, Kristen Grauman, Raquel Urtasun, Tr...
Understanding human emotions is one of the necessary skills for the computer to interact intelligently with human users. The most expressive way humans display emotions is through...
Ira Cohen, Nicu Sebe, Fabio Gagliardi Cozman, Marc...
In this paper we present TANC, i.e., a tree-augmented naive credal classifier based on imprecise probabilities; it models prior near-ignorance via the Extreme Imprecise Dirichlet ...