Learning is using past experiences to inform new behaviors and actions. Because all
experiences are unique, learning always requires some generalization. An effective way of …

A fascinating hypothesis is that human and animal intelligence could be explained by a few
principles (rather than an encyclopaedic list of heuristics). If that hypothesis was correct, we …

We study GPT-3, a recent large language model, using tools from cognitive psychology.
More specifically, we assess GPT-3's decision-making, information search, deliberation, and …

The power of human language and thought arises from systematic compositionality—the
algebraic ability to understand and produce novel combinations from known components …

Reinforcement learning algorithms typically struggle in the absence of a dense, well-shaped
reward function. Intrinsically motivated exploration methods address this limitation by …

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 …

We present a framework for building interactive, real-time, natural language-instructable
robots in the real world, and we open source related assets (dataset, environment …

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined
object categories. This restricted form of supervision limits their generality and usability since …

Contemporary neural networks still fall short of human-level generalization, which extends
far beyond our direct experiences. In this paper, we argue that the underlying cause for this …

Recent research in artificial intelligence and machine learning has largely emphasized
general-purpose learning and ever-larger training sets and more and more compute. In …