Lifelong learning offers a promising paradigm of building a generalist agent that learns and
adapts over its lifespan. Unlike traditional lifelong learning problems in image and text …

The study of zero-shot generalisation (ZSG) in deep Reinforcement Learning (RL) aims to
produce RL algorithms whose policies generalise well to novel unseen situations at …

Training generally-capable agents with reinforcement learning (RL) remains a significant
challenge. A promising avenue for improving the robustness of RL agents is through the use …

The availability of challenging benchmarks has played a key role in the recent progress of
machine learning. In cooperative multi-agent reinforcement learning, the StarCraft Multi …

Foundation models have shown impressive adaptation and scalability in supervised and self-
supervised learning problems, but so far these successes have not fully translated to …

Foundation models have shown impressive adaptation and scalability in supervised and self-
supervised learning problems, but so far these successes have not fully translated to …

Exploring rich environments and evaluating one's actions without prior knowledge is
immensely challenging. In this paper, we propose Motif, a general method to interface such …

The cornerstone of neural algorithmic reasoning is the ability to solve algorithmic tasks,
especially in a way that generalises out of distribution. While recent years have seen a surge …

In recent years, a number of reinforcement learning (RL) methods have been pro-posed to
explore complex environments which differ across episodes. In this work, we show that the …

Reinforcement learning (RL) agents are particularly hard to train when rewards are sparse.
One common solution is to use intrinsic rewards to encourage agents to explore their …