In this article, we aim to provide a literature review of different formulations and approaches
to continual reinforcement learning (RL), also known as lifelong or non-stationary RL. We …

Traditionally, cognitive and computer scientists have viewed intelligence solipsistically, as a
property of unitary agents devoid of social context. Given the success of contemporary …

We present a framework for robot skill acquisition, which 1) efficiently scale up data
generation of language-labelled robot data and 2) effectively distills this data down into a …

Legged locomotion can extend the operational domain of robots to some of the most
challenging environments on Earth. However, conventional controllers for legged …

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 …

Through multi-agent competition, the simple objective of hide-and-seek, and standard
reinforcement learning algorithms at scale, we find that agents create a self-supervised …

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 …

Recent advances in artificial intelligence have been driven by the presence of increasingly
realistic and complex simulated environments. However, many of the existing environments …

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 …

Collecting large amounts of real-world interaction data to train general robotic policies is
often prohibitively expensive, thus motivating the use of simulation data. However, existing …