We study the learnability of sets in Rn under the Gaussian distribution, taking Gaussian surface area as the “complexity measure” of the sets being learned. Let CS denote the ...
Adam R. Klivans, Ryan O'Donnell, Rocco A. Servedio
Rich representations in reinforcement learning have been studied for the purpose of enabling generalization and making learning feasible in large state spaces. We introduce Object...
In this paper, we discuss a technique for handling multi-class problems with binary classifiers, namely to learn one classifier for each pair of classes. Although this idea is kno...
Hierarchical reinforcement learning (RL) is a general framework which studies how to exploit the structure of actions and tasks to accelerate policy learning in large domains. Pri...
Positive transfer learning (TL) occurs when, after gaining experience from learning how to solve a (source) task, the same learner can exploit this experience to improve performanc...