Blog

Research

Discovering when an agent is present in a system

We want to build safe, aligned artificial general intelligence (AGI) systems that pursue the intended goals of its designers. Causal influence diagrams (CIDs) are a way to model decision-making...

Research

Perceiver AR: general-purpose, long-context autoregressive generation

We develop Perceiver AR, an autoregressive, modality-agnostic architecture which uses cross-attention to map long-range inputs to a small number of latents while also maintaining end-to-end causal...

Research

DeepMind’s latest research at ICML 2022

Starting this weekend, the thirty-ninth International Conference on Machine Learning (ICML 2022) is meeting from 17-23 July, 2022 at the Baltimore Convention Center in Maryland, USA, and will be...

Research

Intuitive physics learning in a deep-learning model inspired by developmental psychology

Despite significant effort, current AI systems pale in their understanding of intuitive physics, in comparison to even very young children. In the present work, we address this AI problem,...

Research

Human-centred mechanism design with Democratic AI

In our recent paper, published in Nature Human Behaviour, we provide a proof-of-concept demonstration that deep reinforcement learning (RL) can be used to find economic policies that people will...

Research

BYOL-Explore: Exploration with Bootstrapped Prediction

We present BYOL-Explore, a conceptually simple yet general approach for curiosity-driven exploration in visually-complex environments. BYOL-Explore learns a world representation, the world...

Research

Unlocking High-Accuracy Differentially Private Image Classification through Scale

According to empirical evidence from prior works, utility degradation in DP-SGD becomes more severe on larger neural network models – including the ones regularly used to achieve the best...

Research

Evaluating Multimodal Interactive Agents

In this paper, we assess the merits of these existing evaluation metrics and present a novel approach to evaluation called the Standardised Test Suite (STS). The STS uses behavioural scenarios...

Research

Dynamic language understanding: adaptation to new knowledge in parametric and semi-parametric models

To study how semi-parametric QA models and their underlying parametric language models (LMs) adapt to evolving knowledge, we construct a new large-scale dataset, StreamingQA, with human written...

Research

Open-sourcing MuJoCo

In October 2021, we announced that we acquired the MuJoCo physics simulator, and made it freely available for everyone to support research everywhere. We also committed to developing and...

Research

Emergent Bartering Behaviour in Multi-Agent Reinforcement Learning

In our recent paper, we explore how populations of deep reinforcement learning (deep RL) agents can learn microeconomic behaviours, such as production, consumption, and trading of goods. We find...

Research

A Generalist Agent

Inspired by progress in large-scale language modelling, we apply a similar approach towards building a single generalist agent beyond the realm of text outputs. The agent, which we refer to as...