PAC-MDP algorithms approach the exploration-exploitation problem of reinforcement learning agents in an effective way which guarantees that with high probability, the algorithm pe...
We explore an approach to 3D people tracking with learned motion models and deterministic optimization. The tracking problem is formulated as the minimization of a differentiable ...
In this paper, we address the tradeo between exploration and exploitation for agents which need to learn more about the structure of their environment in order to perform more e e...
Shlomo Argamon-Engelson, Sarit Kraus, Sigalit Sina
In the context of binary classification, we define disagreement as a measure of how often two independently-trained models differ in their classification of unlabeled data. We exp...
A model-free, case-based learning and control algorithm called S-learning is described as implemented in a simulation of a light-seeking mobile robot. S-learning demonstrated learn...