Biological organisms learn from interactions with their environment throughout their lifetime.
For artificial systems to successfully act and adapt in the real world, it is desirable to similarly …

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 …

We introduce Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft
that continuously explores the world, acquires diverse skills, and makes novel discoveries …

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 …

Deep neural networks (DNNs) have had extraordinary successes in classifying
photographic images of objects and are often described as the best models of biological …

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 …

A wide range of reinforcement learning (RL) problems---including robustness, transfer
learning, unsupervised RL, and emergent complexity---require specifying a distribution of …

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 …

Deep reinforcement learning (RL) agents may successfully generalize to new settings if
trained on an appropriately diverse set of environment and task configurations …

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 …