Blog

Research

Learning to Segment Actions from Observation and Narration

We apply a generative segmental model of task structure, guided by narration, to action segmentation in video. We focus on unsupervised and weakly-supervised settings where no action labels are...

Research

Specification gaming: the flip side of AI ingenuity

Specification gaming is a behaviour that satisfies the literal specification of an objective without achieving the intended outcome. We have all had experiences with specification gaming, even if...

Research

Towards understanding glasses with graph neural networks

Under a microscope, a pane of window glass doesn’t look like a collection of orderly molecules, as a crystal would, but rather a jumble with no discernable structure. Glass is made by starting...

Research

Agent57: Outperforming the human Atari benchmark

The Atari57 suite of games is a long-standing benchmark to gauge agent performance across a wide range of tasks. We’ve developed Agent57, the first deep reinforcement learning agent to obtain a...

Research

Visual Grounding in Video for Unsupervised Word Translation

Our goal is to use visual grounding to improve unsupervised word mapping between languages. The key idea is to establish a common visual representation between two languages by learning embeddings...

Research

A new model and dataset for long-range memory

Throughout our lives, we build up memories that are retained over a diverse array of timescales, from minutes to months to years to decades. When reading a book, we can recall characters who were...

Research

Dopamine and temporal difference learning: A fruitful relationship between neuroscience and AI

Learning and motivation are driven by internal and external rewards. Many of our day-to-day behaviours are guided by predicting, or anticipating, whether a given action will result in a positive...

Research

Artificial Intelligence, Values and Alignment

This paper looks at philosophical questions that arise in the context of AI alignment. It defends three propositions. First, normative and technical aspects of the AI alignment problem are...

Research

International evaluation of an AI system for breast cancer screening

Screening mammography aims to identify breast cancer before symptoms appear, enabling earlier therapy for more treatable disease. Despite the existence of screening programs worldwide,...

Research

Learning human objectives by evaluating hypothetical behaviours

When we train reinforcement learning (RL) agents in the real world, we don’t want them to explore unsafe states, such as driving a mobile robot into a ditch or writing an embarrassing email to...

Research

AlphaStar: Grandmaster level in StarCraft II using multi-agent reinforcement learning

AlphaStar is the first AI to reach the top league of a widely popular esport without any game restrictions. This January, a preliminary version of AlphaStar challenged two of the world's top...

Research

Causal Bayesian Networks: A flexible tool to enable fairer machine learning

Decisions based on machine learning (ML) are potentially advantageous over human decisions, as they do not suffer from the same subjectivity, and can be more accurate and easier to analyse. At the...