activity
20112026
most citedOn the difficulty of training Recurrent Neural Networks

3.8k citations · 6.5k across the 44 of their papers we have counts for

collaborators
Showing 2018Show all

13 papers · 1 filter

stat.ML2018

Adapting Auxiliary Losses Using Gradient Similarity

Yunshu Du, Wojciech M. Czarnecki, Siddhant M. Jayakumar +3

One approach to deal with the statistical inefficiency of neural networks is to rely on auxiliary losses that help to build useful representations. However, it is not always trivia…

stat.ML2018

Progress & Compress: A scalable framework for continual learning

Jonathan Schwarz, Jelena Luketina, Wojciech M. Czarnecki +4

We introduce a conceptually simple and scalable framework for continual learning domains where tasks are learned sequentially. Our method is constant in the number of parameters an…

cs.LG2018

Meta-Learning with Latent Embedding Optimization

Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski +4

Gradient-based meta-learning techniques are both widely applicable and proficient at solving challenging few-shot learning and fast adaptation problems. However, they have practica…

cs.LG2018

Relational Deep Reinforcement Learning

Vinicius Zambaldi, David Raposo, Adam Santoro +13

We introduce an approach for deep reinforcement learning (RL) that improves upon the efficiency, generalization capacity, and interpretability of conventional approaches through st…

cs.LG2018

Relational recurrent neural networks

Adam Santoro, Ryan Faulkner, David Raposo +7

Memory-based neural networks model temporal data by leveraging an ability to remember information for long periods. It is unclear, however, whether they also have an ability to per…

cs.LG2018

Mix&Match - Agent Curricula for Reinforcement Learning

Wojciech Marian Czarnecki, Siddhant M. Jayakumar, Max Jaderberg +5

We introduce Mix&Match (M&M) - a training framework designed to facilitate rapid and effective learning in RL agents, especially those that would be too slow or too challenging to…