Reinforcement Learning

In this work, we investigate the properties of data that cause popular representation learning approaches to fail. In particular, we …

Using function approximation to represent a value function is necessary for continuous and high-dimensional state spaces. Linear …

In Reinforcement Learning there is often a need for greater sample efficiency when learning an optimal policy, whether due to the …

We are concerned with the question of how an agent can acquire its own representations from sensory data. We restrict our focus to …

An open problem in artificial intelligence is how to learn and represent knowledge that is sufficient for a general agent that needs to …

Our research project explores the application of AI and machine learning techniques in video games, focusing on procedural content generation and AI-driven advice. We aim to dynamically generate diverse game content and create intelligent virtual companions that offer personalised guidance and strategies to enhance player experiences.

In this line of work, we are interested in techniques that allow an agent to leverage past knowledge to solve new tasks quickly. In particular, we focus on how agents can acquire behaviours that can be combined to generate interesting, novel abilities.

Here we focus on learning abstract representations, which we believe are an important component if we are ever to apply reinforcement learning to the real world. In particular, we focus on skill- and symbol-discovery, as well as the interplay between the two.

We propose a method for autonomously learning an object-centric representation of a continuous and high-dimensional environment that is …

We leverage logical composition in reinforcement learning to create a framework that enables an agent to autonomously determine whether …