Bayesian inference is an appealing approach for leveraging prior knowledge in reinforcement learning (RL). In this paper we describe an algorithm for discovering different classes...
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...
The goal of transfer learning is to use the knowledge acquired in a set of source tasks to improve performance in a related but previously unseen target task. In this paper, we pr...
Manu Sharma, Michael P. Holmes, Juan Carlos Santam...
A scalable architecture to facilitate emergent (self-organized) task decomposition using neural networks and evolutionary algorithms is presented. Various control system architectu...
Jekanthan Thangavelautham, Gabriele M. T. D'Eleute...
Compositional Q-Learning (CQ-L) (Singh 1992) is a modular approach to learning to performcomposite tasks made up of several elemental tasks by reinforcement learning. Skills acqui...