Reinforcement Learning research is traditionally devoted to solve single-task problems. Therefore, anytime a new task is faced, learning must be restarted from scratch. Recently, ...
— Most research in machine learning focuses on scenarios in which a learner faces a single learning task, independently of other learning tasks or prior knowledge. In reality, ho...
Abstract. We propose a novel unsupervised transfer learning framework that utilises unlabelled auxiliary data to quantify and select the most relevant transferrable knowledge for r...
In robot navigation tasks, the representation of the surrounding world plays an important role, especially in reinforcement learning approaches. This work presents a qualitative r...
: ConnectIT uses a graphical representation to express strategies for playing the connect-four game. With this tool we can transfer complex knowledge about the connect-four game it...