Theory & foundations

Publication

Generalised Policy Improvement with Geometric Policy Composition

Shantanu Thakoor, Mark Rowland, Diana Borsa, Will Dabney, Remi Munos, Andre Barreto

ICML

Download

Publication

From Dirichlet to Rubin: Optimistic exploration in RL without bonuses

Daniil Tiapkin *, Denis Belomestny *, Éric Moulines *, Alexey Naumov *, Sergey Samsonov *, Yunhao Tang, Michal Valko, Pierre Menard *

ICML

Download

Publication

Scaling Gaussian process optimization by evaluating a few unique candidates multiple times

Daniele Calandriello, Luigi Carratino *, Alessandro Lazaric *, Lorenzo Rosasco *, Michal Valko

ICML

Download

Publication

An adaptive and efficient multi-goal exploration

Jean Tarbouriech *, Omar Darwiche Domingues *, Pierre Ménard *, Matteo Pirotta *, Michal Valko, Alessandro Lazaric *

AISTATS

Download

Publication

Marginalized operators for off-policy reinforcement learning

Yunhao Tang *, Mark Rowland, Remi Munos, Michal Valko

AISTATS

Download

Publication

Your Policy Regularizer is Secretly an Adversary

Rob Brekelmans *, Tim Genewein, Jordi Grau, Grégoire Delétang, Markus Kunesch, Shane Legg, Pedro Ortega

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

Learning Optimal Conformal Classifiers

David Stutz, Taylan Cemgil, Krishnamurthy Dvijotham *, Arnaud Doucet

ICLR

Download

Publication

Feature and Parameter Selection in Stochastic Linear Bandits

Ahmadreza Moradipari *, Berkay Turan *, Yasin Abbasi Yadkori, Mahnoosh Alizadeh *, Mohammad Ghavamzadeh *

ICML

Download

Publication

On the Role of Neural Collapse in Transfer Learning

Andras Gyorgy, Marcus Hutter

ICLR

Download

Publication

ParK: Sound and Efficient Kernel Ridge Regression by Feature Space Partitions

Luigi Carratino *, Daniele Calandriello, Stefano Vigogna *, Lorenzo Rosasco *

NeurIPS

Download

Publication

On the Expressivity of Markov Reward

David Abel, Doina Precup, Anna Harutyunyan, Mark Ho *, Michael Littman *, Will Dabney, Satinder Baveja

NeurIPS

Download

Publication

Asymptotically Best Casual Effect Identification with Multi-Armed Bandits

Alan Malek, Silvia Chiappa

NeurIPS

Download

Publication

Statistical discrimination in learning agents

Joel Leibo, Yiran Mao, Kevin McKee, William Isaac, Silvia Chiappa, Ben Coppin, Karl Tuyls, Yoram Bachrach, Suzanne Sadedin *, Sasha Vezhnevets, Michiel Bakker

arXiv

Download

Publication

Deep Kernel Shaping

James Martens, Andy Ballard, Guillaume Desjardins, Grzegorz Swirszcz, Valentin Dalibard, Jascha Sohl-Dickstein *, Sam Schoenholz *

arXiv

Download

Publication

Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers

Guodong Zhang, Alex Botev, James Martens

ICLR

Download

Publication

Temporally Abstract Partial Models

Khimya Khetarpal *, Zafarali Ahmed, Gheorghe Comanici, Doina Precup

NeurIPS

Download

Publication

Nonparametric Regression with Shallow Overparameterized Neural Networks Trained by GD with Early Stopping

Ilja Kuzborskij, Csaba Szepesvari

COLT

Download

Publication

Taylor expansions of discount factors

Yunhao Tang *, Remi Munos, Mark Rowland, Michal Valko

ICML

Download

Publication

Kernel-based reinforcement Learning: A finite-time analysis

O Domingues *, Pierre Menard *, Matteo Pirotta *, Emilie Kaufmann *, Michal Valko

ICML

Download

Publication

Online A-optimal design and active linear regression

Xavier Fontaine *, Pierre Perrault *, Michal Valko, V Perchet *

ICML

Download

Publication

Fast active learning for pure exploration in reinforcement learning

Pierre Ménard *, O Domingues *, Emilie Kaufmann *, Anders Jonsson *, Edouard Leurent *, Michal Valko

ICML

Download

Publication

Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers

Luke Marris, Paul Muller, Marc Lanctot, Karl Tuyls, Thore Graepel

ICML

Download

Publication

A Distribution-Dependent Analysis of Meta-Learning

Mikhail Konobeev *, Ilja Kuzborskij, Csaba Szepesvari

ICML

Download

Publication

Learning in two-player zero-sum partially observable Markov games with perfect recall

Tadashi Kozuno *, Pierre Ménard *, Remi Munos, Michal Valko

NeurIPS

Download

Publications

Theory & foundations