85 citations · 295 across the 16 of their papers we have counts for
17 papers
Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset
Alexandre Galashov, Michalis K. Titsias, András György +4
Neural networks are traditionally trained under the assumption that data come from a stationary distribution. However, settings which violate this assumption are becoming more popu…
Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models
Amal Rannen-Triki, Jorg Bornschein, Razvan Pascanu +5
We consider the problem of online fine tuning the parameters of a language model at test time, also known as dynamic evaluation. While it is generally known that this approach impr…
Kalman Filter for Online Classification of Non-Stationary Data
Michalis K. Titsias, Alexandre Galashov, Amal Rannen-Triki +3
In Online Continual Learning (OCL) a learning system receives a stream of data and sequentially performs prediction and training steps. Important challenges in OCL are concerned wi…
Towards Compute-Optimal Transfer Learning
Massimo Caccia, Alexandre Galashov, Arthur Douillard +6
The field of transfer learning is undergoing a significant shift with the introduction of large pretrained models which have demonstrated strong adaptability to a variety of downst…
NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research
Jorg Bornschein, Alexandre Galashov, Ross Hemsley +17
A shared goal of several machine learning communities like continual learning, meta-learning and transfer learning, is to design algorithms and models that efficiently and robustly…
Data augmentation for efficient learning from parametric experts
Alexandre Galashov, Josh Merel, Nicolas Heess
We present a simple, yet powerful data-augmentation technique to enable data-efficient learning from parametric experts for reinforcement and imitation learning. We focus on what w…
Game Plan: What AI can do for Football, and What Football can do for AI
Karl Tuyls, Shayegan Omidshafiei, Paul Muller +33
The rapid progress in artificial intelligence (AI) and machine learning has opened unprecedented analytics possibilities in various team and individual sports, including baseball,…
Behavior Priors for Efficient Reinforcement Learning
Dhruva Tirumala, Alexandre Galashov, Hyeonwoo Noh +8
As we deploy reinforcement learning agents to solve increasingly challenging problems, methods that allow us to inject prior knowledge about the structure of the world and effectiv…
Learning Dexterous Manipulation from Suboptimal Experts
Rae Jeong, Jost Tobias Springenberg, Jackie Kay +5
Learning dexterous manipulation in high-dimensional state-action spaces is an important open challenge with exploration presenting a major bottleneck. Although in many cases the le…
Temporal Difference Uncertainties as a Signal for Exploration
Sebastian Flennerhag, Jane X. Wang, Pablo Sprechmann +7
An effective approach to exploration in reinforcement learning is to rely on an agent's uncertainty over the optimal policy, which can yield near-optimal exploration strategies in…
Importance Weighted Policy Learning and Adaptation
Alexandre Galashov, Jakub Sygnowski, Guillaume Desjardins +5
The ability to exploit prior experience to solve novel problems rapidly is a hallmark of biological learning systems and of great practical importance for artificial ones. In the m…
Task Agnostic Continual Learning via Meta Learning
Xu He, Jakub Sygnowski, Alexandre Galashov +3
While neural networks are powerful function approximators, they suffer from catastrophic forgetting when the data distribution is not stationary. One particular formalism that stud…
Information asymmetry in KL-regularized RL
Alexandre Galashov, Siddhant M. Jayakumar, Leonard Hasenclever +7
Many real world tasks exhibit rich structure that is repeated across different parts of the state space or in time. In this work we study the possibility of leveraging such repeate…
Meta reinforcement learning as task inference
Jan Humplik, Alexandre Galashov, Leonard Hasenclever +3
Humans achieve efficient learning by relying on prior knowledge about the structure of naturally occurring tasks. There is considerable interest in designing reinforcement learning…
Meta-Learning surrogate models for sequential decision making
Alexandre Galashov, Jonathan Schwarz, Hyunjik Kim +5
We introduce a unified probabilistic framework for solving sequential decision making problems ranging from Bayesian optimisation to contextual bandits and reinforcement learning.…
Exploiting Hierarchy for Learning and Transfer in KL-regularized RL
Dhruva Tirumala, Hyeonwoo Noh, Alexandre Galashov +6
As reinforcement learning agents are tasked with solving more challenging and diverse tasks, the ability to incorporate prior knowledge into the learning system and to exploit reus…
Neural probabilistic motor primitives for humanoid control
Josh Merel, Leonard Hasenclever, Alexandre Galashov +5
We focus on the problem of learning a single motor module that can flexibly express a range of behaviors for the control of high-dimensional physically simulated humanoids. To do t…