122 citations · 240 across the 10 of their papers we have counts for
10 papers
On the impressive performance of randomly weighted encoders in summarization tasks
Jonathan Pilault, Jaehong Park, Christopher Pal
In this work, we investigate the performance of untrained randomly initialized encoders in a general class of sequence to sequence models and compare their performance with that of…
Curriculum in Gradient-Based Meta-Reinforcement Learning
Bhairav Mehta, Tristan Deleu, Sharath Chandra Raparthy +2
Gradient-based meta-learners such as Model-Agnostic Meta-Learning (MAML) have shown strong few-shot performance in supervised and reinforcement learning settings. However, specific…
Reinforced active learning for image segmentation
Arantxa Casanova, Pedro O. Pinheiro, Negar Rostamzadeh +1
Learning-based approaches for semantic segmentation have two inherent challenges. First, acquiring pixel-wise labels is expensive and time-consuming. Second, realistic segmentation…
Finding and Visualizing Weaknesses of Deep Reinforcement Learning Agents
Christian Rupprecht, Cyril Ibrahim, Christopher J. Pal
As deep reinforcement learning driven by visual perception becomes more widely used there is a growing need to better understand and probe the learned agents. Understanding the dec…
Active Domain Randomization
Bhairav Mehta, Manfred Diaz, Florian Golemo +2
Domain randomization is a popular technique for improving domain transfer, often used in a zero-shot setting when the target domain is unknown or cannot easily be used for training…
A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
Yoshua Bengio, Tristan Deleu, Nasim Rahaman +5
We propose to meta-learn causal structures based on how fast a learner adapts to new distributions arising from sparse distributional changes, e.g. due to interventions, actions of…