Charles Blundell

research

∙ 05/02/2023

Unlocking the Power of Representations in Long-term Novelty-based Exploration

We introduce Robust Exploration via Clustering-based Online Density Esti...

0 Alaa Saade, et al. ∙

research

∙ 02/20/2023

Neural Algorithmic Reasoning with Causal Regularisation

Recent work on neural algorithmic reasoning has investigated the reasoni...

0 Beatrice Bevilacqua, et al. ∙

research

∙ 01/12/2023

SemPPL: Predicting pseudo-labels for better contrastive representations

Learning from large amounts of unsupervised data and a small amount of s...

0 Matko Bošnjak, et al. ∙

research

∙ 09/22/2022

A Generalist Neural Algorithmic Learner

The cornerstone of neural algorithmic reasoning is the ability to solve ...

6 Borja Ibarz, et al. ∙

research

∙ 09/15/2022

Human-level Atari 200x faster

The task of building general agents that perform well over a wide range ...

0 Steven Kapturowski, et al. ∙

research

∙ 05/31/2022

The CLRS Algorithmic Reasoning Benchmark

Learning representations of algorithms is an emerging area of machine le...

0 Petar Veličković, et al. ∙

research

∙ 02/17/2022

Retrieval-Augmented Reinforcement Learning

Most deep reinforcement learning (RL) algorithms distill experience into...

0 Anirudh Goyal, et al. ∙

research

∙ 01/13/2022

Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?

Despite recent progress made by self-supervised methods in representatio...

0 Nenad Tomašev, et al. ∙

research

∙ 11/16/2021

Normalizing flows for atomic solids

We present a machine-learning approach, based on normalizing flows, for ...

0 Peter Wirnsberger, et al. ∙

research

∙ 07/12/2021

CoBERL: Contrastive BERT for Reinforcement Learning

Many reinforcement learning (RL) agents require a large amount of experi...

10 Andrea Banino, et al. ∙

research

∙ 07/12/2021

PonderNet: Learning to Ponder

In standard neural networks the amount of computation used grows with th...

0 Andrea Banino, et al. ∙

research

∙ 06/21/2021

Emphatic Algorithms for Deep Reinforcement Learning

Off-policy learning allows us to learn about possible policies of behavi...

0 Ray Jiang, et al. ∙

research

∙ 05/06/2021

Neural Algorithmic Reasoning

Algorithms have been fundamental to recent global technological advances...

0 Petar Veličković, et al. ∙

research

∙ 03/02/2021

Neural Production Systems

Visual environments are structured, consisting of distinct objects or en...

12 Anirudh Goyal, et al. ∙

research

∙ 03/01/2021

Coordination Among Neural Modules Through a Shared Global Workspace

Deep learning has seen a movement away from representing examples with a...

14 Anirudh Goyal, et al. ∙

research

∙ 03/01/2021

Persistent Message Passing

Graph neural networks (GNNs) are a powerful inductive bias for modelling...

0 Heiko Strathmann, et al. ∙

research

∙ 10/15/2020

Representation Learning via Invariant Causal Mechanisms

Self-supervised learning has emerged as a strategy to reduce the relianc...

3 Jovana Mitrovic, et al. ∙

research

∙ 06/29/2020

Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems

Modeling a structured, dynamic environment like a video game requires ke...

0 Anirudh Goyal, et al. ∙

research

∙ 06/11/2020

Pointer Graph Networks

Graph neural networks (GNNs) are typically applied to static graphs that...

33 Petar Veličković, et al. ∙

research

∙ 03/30/2020

Agent57: Outperforming the Atari Human Benchmark

Atari games have been a long-standing benchmark in the reinforcement lea...

9 Adrià Puigdomènech Badia, et al. ∙

research

∙ 02/14/2020

Never Give Up: Learning Directed Exploration Strategies

We propose a reinforcement learning agent to solve hard exploration game...

7 Adrià Puigdomènech Badia, et al. ∙

research

∙ 02/12/2020

Targeted free energy estimation via learned mappings

Free energy perturbation (FEP) was proposed by Zwanzig more than six dec...

1 Peter Wirnsberger, et al. ∙

research

∙ 01/29/2020

MEMO: A Deep Network for Flexible Combination of Episodic Memories

Recent research developing neural network architectures with external me...

16 Andrea Banino, et al. ∙

research

∙ 12/12/2019

Shaping representations through communication: community size effect in artificial learning systems

Motivated by theories of language and communication that explain why com...

6 Olivier Tieleman, et al. ∙

research

∙ 10/29/2019

Generalization of Reinforcement Learners with Working and Episodic Memory

Memory is an important aspect of intelligence and plays a role in many d...

26 Meire Fortunato, et al. ∙

research

∙ 10/23/2019

Neural Execution of Graph Algorithms

Graph Neural Networks (GNNs) are a powerful representational tool for so...

0 Petar Veličković, et al. ∙

research

∙ 10/18/2018

Fast deep reinforcement learning using online adjustments from the past

We propose Ephemeral Value Adjusments (EVA): a means of allowing deep re...

0 Steven Hansen, et al. ∙

research

∙ 05/24/2018

Been There, Done That: Meta-Learning with Episodic Recall

Meta-learning agents excel at rapidly learning new tasks from open-ended...

0 Samuel Ritter, et al. ∙

research

∙ 05/23/2018

Pushing the bounds of dropout

We show that dropout training is best understood as performing MAP estim...

0 Gábor Melis, et al. ∙

research

∙ 02/28/2018

Memory-based Parameter Adaptation

Deep neural networks have excelled on a wide range of problems, from vis...

0 Pablo Sprechmann, et al. ∙

research

∙ 07/26/2017

DARLA: Improving Zero-Shot Transfer in Reinforcement Learning

Domain adaptation is an important open problem in deep reinforcement lea...

0 Irina Higgins, et al. ∙

research

∙ 06/30/2017

Noisy Networks for Exploration

We introduce NoisyNet, a deep reinforcement learning agent with parametr...

0 Meire Fortunato, et al. ∙

research

∙ 04/10/2017

Bayesian Recurrent Neural Networks

In this work we explore a straightforward variational Bayes scheme for R...

0 Meire Fortunato, et al. ∙

research

∙ 03/06/2017

Neural Episodic Control

Deep reinforcement learning methods attain super-human performance in a ...

0 Alexander Pritzel, et al. ∙

research

∙ 01/30/2017

PathNet: Evolution Channels Gradient Descent in Super Neural Networks

For artificial general intelligence (AGI) it would be efficient if multi...

0 Chrisantha Fernando, et al. ∙

research

∙ 11/17/2016

Learning to reinforcement learn

In recent years deep reinforcement learning (RL) systems have attained s...

0 Jane X Wang, et al. ∙

research

∙ 06/17/2016

Early Visual Concept Learning with Unsupervised Deep Learning

Automated discovery of early visual concepts from raw image data is a ma...

0 Irina Higgins, et al. ∙

research

∙ 06/14/2016

Model-Free Episodic Control

State of the art deep reinforcement learning algorithms take many millio...

0 Charles Blundell, et al. ∙

research

∙ 06/13/2016

Matching Networks for One Shot Learning

Learning from a few examples remains a key challenge in machine learning...

0 Oriol Vinyals, et al. ∙

research

∙ 02/15/2016

Deep Exploration via Bootstrapped DQN

Efficient exploration in complex environments remains a major challenge ...

0 Ian Osband, et al. ∙

research

∙ 12/31/2015

Distributed Bayesian Learning with Stochastic Natural-gradient Expectation Propagation and the Posterior Server

This paper makes two contributions to Bayesian machine learning algorith...

0 Leonard Hasenclever, et al. ∙

research

∙ 05/20/2015

Weight Uncertainty in Neural Networks

We introduce a new, efficient, principled and backpropagation-compatible...

0 Charles Blundell, et al. ∙

research

∙ 11/11/2014

The Bayesian Echo Chamber: Modeling Social Influence via Linguistic Accommodation

We present the Bayesian Echo Chamber, a new Bayesian generative model fo...

0 Fangjian Guo, et al. ∙

research

∙ 03/15/2012

Bayesian Rose Trees

Hierarchical structure is ubiquitous in data across many domains. There ...

0 Charles Blundell, et al. ∙

research

∙ 08/31/2010

Mixed Cumulative Distribution Networks

Directed acyclic graphs (DAGs) are a popular framework to express multiv...

0 Ricardo Silva, et al. ∙

Charles Blundell

Featured Co-authors