b'Joelle Pineau'

research

∙ 10/23/2022

The Curious Case of Absolute Position Embeddings

Transformer language models encode the notion of word order using positi...

0 Koustuv Sinha, et al. ∙

research

∙ 06/21/2022

Questions Are All You Need to Train a Dense Passage Retriever

We introduce ART, a new corpus-level autoencoding approach for training ...

6 Devendra Singh Sachan, et al. ∙

research

∙ 04/15/2022

Improving Passage Retrieval with Zero-Shot Question Generation

We propose a simple and effective re-ranking method for improving passag...

0 Devendra Singh Sachan, et al. ∙

research

∙ 03/08/2022

New Insights on Reducing Abrupt Representation Change in Online Continual Learning

In the online continual learning paradigm, agents must learn from a chan...

3 Lucas Caccia, et al. ∙

research

∙ 02/28/2022

Estimating causal effects with optimization-based methods: A review and empirical comparison

In the absence of randomized controlled and natural experiments, it is n...

15 Martin Cousineau, et al. ∙

research

∙ 02/20/2022

Efficient Continual Learning Ensembles in Neural Network Subspaces

A growing body of research in continual learning focuses on the catastro...

5 Thang Doan, et al. ∙

research

∙ 02/14/2022

Robust Policy Learning over Multiple Uncertainty Sets

Reinforcement learning (RL) agents need to be robust to variations in sa...

2 Annie Xie, et al. ∙

research

∙ 01/05/2022

A Generalized Bootstrap Target for Value-Learning, Efficiently Combining Value and Feature Predictions

Estimating value functions is a core component of reinforcement learning...

8 Anthony GX-Chen, et al. ∙

research

∙ 10/13/2021

Block Contextual MDPs for Continual Learning

In reinforcement learning (RL), when defining a Markov Decision Process ...

8 Shagun Sodhani, et al. ∙

research

∙ 06/21/2021

OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation

We consider the offline reinforcement learning (RL) setting where the ag...

10 Jongmin Lee, et al. ∙

research

∙ 06/20/2021

Do Encoder Representations of Generative Dialogue Models Encode Sufficient Information about the Task ?

Predicting the next utterance in dialogue is contingent on encoding of u...

11 Prasanna Parthasarathi, et al. ∙

research

∙ 06/20/2021

A Brief Study on the Effects of Training Generative Dialogue Models with a Semantic loss

Neural models trained for next utterance generation in dialogue task lea...

6 Prasanna Parthasarathi, et al. ∙

research

∙ 06/16/2021

SPeCiaL: Self-Supervised Pretraining for Continual Learning

This paper presents SPeCiaL: a method for unsupervised pretraining of re...

8 Lucas Caccia, et al. ∙

research

∙ 06/07/2021

Correcting Momentum in Temporal Difference Learning

A common optimization tool used in deep reinforcement learning is moment...

26 Emmanuel Bengio, et al. ∙

research

∙ 05/31/2021

Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs

We study the problem of Safe Policy Improvement (SPI) under constraints ...

5 Harsh Satija, et al. ∙

research

∙ 04/15/2021

Sometimes We Want Translationese

Rapid progress in Neural Machine Translation (NMT) systems over the last...

5 Prasanna Parthasarathi, et al. ∙

research

∙ 04/14/2021

Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little

A possible explanation for the impressive performance of masked language...

7 Koustuv Sinha, et al. ∙

research

∙ 04/11/2021

Reducing Representation Drift in Online Continual Learning

We study the online continual learning paradigm, where agents must learn...

0 Lucas Caccia, et al. ∙

research

∙ 03/14/2021

Quasi-Equivalence Discovery for Zero-Shot Emergent Communication

Effective communication is an important skill for enabling information e...

9 Kalesha Bullard, et al. ∙

research

∙ 02/19/2021

Model-Invariant State Abstractions for Model-Based Reinforcement Learning

Accuracy and generalization of dynamics models is key to the success of ...

2 Manan Tomar, et al. ∙

research

∙ 02/14/2021

Domain Adversarial Reinforcement Learning

We consider the problem of generalization in reinforcement learning wher...

8 Bonnie Li, et al. ∙

research

∙ 02/11/2021

Multi-Task Reinforcement Learning with Context-based Representations

The benefit of multi-task learning over single-task learning relies on t...

18 Shagun Sodhani, et al. ∙

research

∙ 02/05/2021

Exploring the Limits of Few-Shot Link Prediction in Knowledge Graphs

Real-world knowledge graphs are often characterized by low-frequency rel...

2 Dora Jambor, et al. ∙

research

∙ 01/13/2021

COVID-19 Deterioration Prediction via Self-Supervised Representation Learning and Multi-Image Prediction

The rapid spread of COVID-19 cases in recent months has strained hospita...

12 Anuroop Sriram, et al. ∙

research

∙ 12/30/2020

Unnatural Language Inference

Natural Language Understanding has witnessed a watershed moment with the...

5 Koustuv Sinha, et al. ∙

research

∙ 12/03/2020

Intervention Design for Effective Sim2Real Transfer

The goal of this work is to address the recent success of domain randomi...

2 Melissa Mozifian, et al. ∙

research

∙ 10/29/2020

Exploring Zero-Shot Emergent Communication in Embodied Multi-Agent Populations

Effective communication is an important skill for enabling information e...

13 Kalesha Bullard, et al. ∙

research

∙ 10/07/2020

Regularized Inverse Reinforcement Learning

Inverse Reinforcement Learning (IRL) aims to facilitate a learner's abil...

0 Wonseok Jeon, et al. ∙

research

∙ 09/28/2020

Novelty Search in representational space for sample efficient exploration

We present a new approach for efficient exploration which leverages a lo...

0 Ruo Yu Tao, et al. ∙

research

∙ 08/26/2020

Constrained Markov Decision Processes via Backward Value Functions

Although Reinforcement Learning (RL) algorithms have found tremendous su...

6 Harsh Satija, et al. ∙

research

∙ 08/24/2020

How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics

Though generative dialogue modeling is widely seen as a language modelin...

11 Prasanna Parthasarathi, et al. ∙

research

∙ 07/14/2020

Multi-Task Reinforcement Learning as a Hidden-Parameter Block MDP

Multi-task reinforcement learning is a rich paradigm where information f...

16 Amy Zhang, et al. ∙

research

∙ 07/06/2020

TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning?

We investigate whether Jacobi preconditioning, accounting for the bootst...

0 Joshua Romoff, et al. ∙

research

∙ 07/03/2020

Deep interpretability for GWAS

Genome-Wide Association Studies are typically conducted using linear mod...

1 Deepak Sharma, et al. ∙

research

∙ 06/23/2020

Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization

Adversarial imitation learning alternates between learning a discriminat...

15 Paul Barde, et al. ∙

research

∙ 05/07/2020

Plan2Vec: Unsupervised Representation Learning by Latent Plans

In this paper we introduce plan2vec, an unsupervised representation lear...

8 Ge Yang, et al. ∙

research

∙ 05/06/2020

A Large-Scale, Open-Domain, Mixed-Interface Dialogue-Based ITS for STEM

We present Korbit, a large-scale, open-domain, mixed-interface, dialogue...

1 Iulian Vlad Serban, et al. ∙

research

∙ 05/05/2020

Automated Personalized Feedback Improves Learning Gains in an Intelligent Tutoring System

We investigate how automated, data-driven, personalized feedback in a la...

8 Ekaterina Kochmar, et al. ∙

research

∙ 05/01/2020

Learning an Unreferenced Metric for Online Dialogue Evaluation

Evaluating the quality of a dialogue interaction between two agents is a...

0 Koustuv Sinha, et al. ∙

research

∙ 03/27/2020

Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)

One of the challenges in machine learning research is to ensure that pre...

0 Joelle Pineau, et al. ∙

research

∙ 03/14/2020

Evaluating Logical Generalization in Graph Neural Networks

Recent research has highlighted the role of relational inductive biases ...

9 Koustuv Sinha, et al. ∙

research

∙ 03/13/2020

Interference and Generalization in Temporal Difference Learning

We study the link between generalization and interference in temporal-di...

7 Emmanuel Bengio, et al. ∙

research

∙ 03/12/2020

Invariant Causal Prediction for Block MDPs

Generalization across environments is critical to the successful applica...

2 Amy Zhang, et al. ∙

research

∙ 03/09/2020

Stable Policy Optimization via Off-Policy Divergence Regularization

Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization...

6 Ahmed Touati, et al. ∙

research

∙ 02/28/2020

The importance of transparency and reproducibility in artificial intelligence research

In their study, McKinney et al. showed the high potential of artificial ...

0 Benjamin Haibe-Kains, et al. ∙

research

∙ 02/24/2020

Scalable Multi-Agent Inverse Reinforcement Learning via Actor-Attention-Critic

Multi-agent adversarial inverse reinforcement learning (MA-AIRL) is a re...

0 Wonseok Jeon, et al. ∙

research

∙ 02/07/2020

Provably efficient reconstruction of policy networks

Recent research has shown that learning poli-cies parametrized by large ...

18 Bogdan Mazoure, et al. ∙

research

∙ 01/31/2020

Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning

Accurate reporting of energy and carbon usage is essential for understan...

0 Peter Henderson, et al. ∙

research

∙ 11/20/2019

Exploiting Spatial Invariance for Scalable Unsupervised Object Tracking

The ability to detect and track objects in the visual world is a crucial...

14 Eric Crawford, et al. ∙

research

∙ 11/19/2019

Online Learned Continual Compression with Stacked Quantization Module

We introduce and study the problem of Online Continual Compression, wher...

12 Lucas Caccia, et al. ∙

Joelle Pineau

Featured Co-authors