1.7k citations · 3k across the 42 of their papers we have counts for
10 papers · 1 filter
Think Before You Act: Decision Transformers with Working Memory
Jikun Kang, Romain Laroche, Xingdi Yuan +3
Decision Transformer-based decision-making agents have shown the ability to generalize across multiple tasks. However, their performance relies on massive data and computation. We…
Role-Wise Data Augmentation for Knowledge Distillation
Jie Fu, Xue Geng, Zhijian Duan +6
Knowledge Distillation (KD) is a common method for transferring the ``knowledge'' learned by one machine learning model (the \textit{teacher}) into another model (the \textit{stude…
A Study of State Aliasing in Structured Prediction with RNNs
Layla El Asri, Adam Trischler
End-to-end reinforcement learning agents learn a state representation and a policy at the same time. Recurrent neural networks (RNNs) have been trained successfully as reinforcemen…
An Empirical Study of Example Forgetting during Deep Neural Network Learning
Mariya Toneva, Alessandro Sordoni, Remi Tachet des Combes +3
Inspired by the phenomenon of catastrophic forgetting, we investigate the learning dynamics of neural networks as they train on single classification tasks. Our goal is to understa…
How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG
Paul Trichelair, Ali Emami, Adam Trischler +2
Recent studies have significantly improved the state-of-the-art on common-sense reasoning (CSR) benchmarks like the Winograd Schema Challenge (WSC) and SWAG. The question we ask in…
TextWorld: A Learning Environment for Text-based Games
Marc-Alexandre Côté, Ákos Kádár, Xingdi Yuan +10
We introduce TextWorld, a sandbox learning environment for the training and evaluation of RL agents on text-based games. TextWorld is a Python library that handles interactive play…
Rapid Adaptation with Conditionally Shifted Neurons
Tsendsuren Munkhdalai, Xingdi Yuan, Soroush Mehri +1
We describe a mechanism by which artificial neural networks can learn rapid adaptation - the ability to adapt on the fly, with little data, to new tasks - that we call conditionall…
Plan, Attend, Generate: Planning for Sequence-to-Sequence Models
Francis Dutil, Caglar Gulcehre, Adam Trischler +1
We investigate the integration of a planning mechanism into sequence-to-sequence models using attention. We develop a model which can plan ahead in the future when it computes its…
Learning Algorithms for Active Learning
Philip Bachman, Alessandro Sordoni, Adam Trischler
We introduce a model that learns active learning algorithms via metalearning. For a distribution of related tasks, our model jointly learns: a data representation, an item selectio…
Towards Information-Seeking Agents
Philip Bachman, Alessandro Sordoni, Adam Trischler
We develop a general problem setting for training and testing the ability of agents to gather information efficiently. Specifically, we present a collection of tasks in which succe…