In some environments, a learning agent must learn to balance competing objectives. For example, a Q-learner agent may need to learn which choices expose the agent to risk and whic...
Many semi-supervised learning algorithms only
deal with binary classification. Their extension to the
multi-class problem is usually obtained by repeatedly
solving a set of bina...
—We address the problem of comparing sets of images for object recognition, where the sets may represent variations in an object’s appearance due to changing camera pose and li...
Abstract. We consider the problem of detecting a large number of different classes of objects in cluttered scenes. We present a learning procedure, based on boosted decision stumps...
Antonio B. Torralba, Kevin P. Murphy, William T. F...
We consider the problem of multi-task reinforcement learning where the learner is provided with a set of tasks, for which only a small number of samples can be generated for any g...