Research

Publication

Meta-Gradients in Nonstationary Environments

Jelena Luketina *, Tom Zahavy, Sebastian Flennerhag, Yannick Schroecker, David Abel, Satinder Baveja

arXiv

Download

Publication

Reconstructing Training Data with Informed Adversaries: Attacks and Mitigations

Borja De Balle Pigem, Giovanni Cherubin *, Jamie Hayes

IEEE Symposium on Security and Privacy

Download

Publication

Learning Robust Real-Time Cultural Transmission without Human Data

Cultural General Intelligence Team

arXiv

Download

Publication

Learning Equilibria in Mean-Field Games: Introducing Mean-Field PSRO

Paul Muller, Mark Rowland, Romuald Elie, Julien Perolat, Karl Tuyls, G Piliouras *, Olivier Pietquin, M Lauriere *, Raphael Marinier *

AAMAS

Download

Publication

Probing Image-Language Transformers for Verb Understanding

Lisa Anne Hendricks, Aida Nematzadeh

arXiv

Download

Publication

Message passing all the way up

Petar Veličković

arXiv

Download

Publication

Magnetic Control of Tokamak Plasmas Through Deep Reinforcement Learning

Jonas Degrave, Federico Felici *, Jonas Buchli, Michael Neunert, Brendan Tracey, Francesco Carpanese *, Timo Ewalds, Roland Hafner, Abbas Abdolmaleki, Diego de Las Casas, Craig Donner, Leslie Fritz, Cristian Galperti *, Andrea Huber, James Keeling, Maria Tsimpoukelli *, Jackie Kay, Antoine Merle *, Jean-Marc Moret *, Seb Noury, Federico Pesamosca *, David Pfau, Olivier Sauter *, Cristian Sommariva *, Stefano Coda *, Basil Duval *, Ambrogio Fasoli *, Pushmeet Kohli, Koray Kavukcuoglu, Demis Hassabis, Martin Riedmiller

Nature

Download

Publication

Large-scale representation learning on graphs via bootstrapping

Shantanu Thakoor, Corentin Tallec, Mohammad Gheshlaghi Azar, Mehdi Azabou *, Eva Dyer *, Remi Munos, Petar Veličković, Michal Valko

ICLR

Download

Publication

Abstraction for Deep Reinforcement Learning

Murray Shanahan, Melanie Mitchell *

arXiv

Download

Publication

Competition-Level Code Generation using Deep Language Models

Yujia Li, David Choi, Junyoung Chung, Nate Kushman, Julian Schrittwieser, Rémi Leblond, Tom Eccles, James Keeling, Felix Gimeno, Agustin Dal Lago, Thomas Hubert, Peter Choy, Cyprien de Masson d'Autume, Igor Babuschkin, Po-Sen Huang, Johannes Welbl, Sven Gowal, Alexey Cherepanov, James Molloy, Daniel J. Mankowitz, Esme Sutherland Robson, Pushmeet Kohli, Nando de Freitas, Koray Kavukcuoglu, Oriol Vinyals

arXiv

Download

Publication

Red Teaming Language Models with Language Models

Ethan Perez, Saffron Huang, Francis Song, Trevor Cai, Roman Ring, John Aslanides, Amelia Glaese, Nat McAleese, Geoffrey Irving

arXiv

Download

Publication

Sample-based Approximation of Nash in Large Many-Player Games via Gradient Descent

Ian Gemp, Rahul Savani *, Marc Lanctot, Yoram Bachrach, Thomas Anthony, Richard Everett, Andrea Tacchetti, Tom Eccles, János Kramár

AAMAS

Download

Publication

Online Apprenticeship Learning

Lior Shani *, Tom Zahavy, Shie Mannor *

AAAI

Download

Publication

Physical Design using Differentiable Learned Simulators

Kelsey Allen, Tatiana Guevara, Kimberly Stachenfeld, Alvaro Sanchez, Peter Battaglia, Jessica Hamrick, Tobias Pfaff

arXiv

Download

Publication

Warmth and competence in human-agent cooperation

Kevin McKee, Xuechunzi Bai *, Susan Fiske *

AAMAS

Download

Publication

NeuPL: Neural Population Learning

Siqi Liu, Luke Marris, Daniel Hennes, Josh Merel *, Nicolas Heess, Thore Graepel *

ICLR

Download

Publication

Learning more skills through optimistic exploration

DJ Strouse, Kate Baumli, David Warde-Farley, Vlad Mnih, Steven Hansen

ICLR

Download

Publication

Human-centred mechanism design with democratic AI research

Raphael Koster, Jan Balaguer, Andrea Tacchetti, Ari Weinstein, Lucy Campbell-Gillingham, Phoebe Thacker, Duncan Williams, Matt Botvinick, Christopher Summerfield, Oliver Hauser *

arXiv

Download

Publication

Spurious normativity enhances learning of compliance and enforcement behavior in artificial agents

Raphael Koster, Dylan Hadfield-Menell *, Richard Everett, Laura Weidinger, G Hadfield *, Joel Leibo

PNAS

Download

Publication

Chaining Value Functions for Off-Policy Learning

Simon Schmitt, John Shawe-Taylor *, Hado van Hasselt

AAAI

Download

Publication

Pavlovian Signalling with General Value Functions in Agent-Agent Temporal Decision Making

Andrew Butcher, Mike Johanson, Elnaz Davoodi, Dylan Brenneis, Adam S. R. Parker *, Leslie Acker, Joseph Modayil, Adam White, Patrick Pilarski

arXiv

Download

Publication

Learning to be robust and private

Jamie Hayes, Borja De Balle Pigem, Pawan Mudigonda

arXiv

Download

Publication

Learned coarse models for efficient turbulence simulation

Kimberly Stachenfeld, Drummond Fielding *, Dmitrii Kochkov *, Miles Cranmer, Tobias Pfaff, Jonathan Godwin, Elaine Cui *, Shirley Ho *, Peter Battaglia, Alvaro Sanchez

ICLR

Download

Publication

On the Role of Neural Collapse in Transfer Learning

Andras Gyorgy, Marcus Hutter

ICLR

Download

Publication

Assessing Human Interaction in Virtual Reality with Continually Learning Prediction Agents Based on Reinforcement Learning Algorithms: A Pilot Study

Dylan Brenneis, Andrew Butcher, Elnaz Davoodi, Mike Johanson, Leslie Acker, Matt Botvinick, Joseph Modayil, Adam White, Patrick Pilarski, Adam S. R. Parker *

arXiv

Download