We propose a new approach for reinforcement learning in problems with continuous actions. Actions are sampled by means of a diffusion tree, which generates samples in the continuou...
Christian Vollmer, Erik Schaffernicht, Horst-Micha...
Abstract. Human action is goal-directed and must thus be guided by anticipations of wanted action effects. How anticipatory action control is possible and how it can emerge from ex...
In this paper, we present a Case Based Reasoning (CBR) system for the retrieval of medical cases made up of a series of images with semantic information (such as the patient age, ...
Much emphasis in multiagent reinforcement learning (MARL) research is placed on ensuring that MARL algorithms (eventually) converge to desirable equilibria. As in standard reinfor...
This paper addresses exact learning of Bayesian network structure from data and expert's knowledge based on score functions that are decomposable. First, it describes useful ...