In order to claim fully general intelligence in an autonomous agent, the ability to learn is one of the most central capabilities. Classical machine learning techniques have had ma...
In this paper, we show how reinforcement learning can be applied to real robots to achieve optimal robot behavior. As example, we enable an autonomous soccer robot to learn interce...
Transfer learning problems are typically framed as leveraging knowledge learned on a source task to improve learning on a related, but different, target task. Current transfer met...
We present a framework for knowledge transfer from one reinforcement learning task to a related task through advicetaking mechanisms. We discuss the importance of transfer in comp...
Lisa Torrey, Trevor Walker, Jude W. Shavlik, Richa...
A typical goal for transfer learning algorithms is to utilize knowledge gained in a source task to learn a target task faster. Recently introduced transfer methods in reinforcemen...