Joelle Pineau

Core Academic Member

jpineau@mila.quebec

Canada CIFAR AI Chair

Associate Professor, McGill University, School of Computer Science

Co-Manager Director, Meta AI (FAIR - Facebook AI Research)

Research Topics

Medical Machine Learning

Natural Language Processing

Reinforcement Learning

Website

Google Scholar

Biography

Joelle Pineau is a professor and William Dawson Scholar at the School of Computer Science, McGill University, where she co-directs the Reasoning and Learning Lab. She is a core academic member of Mila – Quebec Artificial Intelligence Institute, a Canada CIFAR AI Chair, and Chief AI Officer at Cohere. Pineau holds a BSc in systems design engineering from the University of Waterloo, and an MSc and PhD in robotics from Carnegie Mellon University.

Her research focuses on developing new models and algorithms for planning and learning in complex partially observable domains. She also works on applying these algorithms to complex problems in robotics, health care, games and conversational agents. In addition to being on the editorial board of the Journal of Machine Learning Research and past president of the International Machine Learning Society, Pineau is the recipient of numerous awards and honours: NSERC’s E.W.R. Steacie Memorial Fellowship (2018), Governor General Innovation Award (2019), Fellow of the Association for the Advancement of Artificial Intelligence (AAAI), Senior Fellow of the Canadian Institute for Advanced Research (CIFAR), and Fellow of the Royal Society of Canada.

Current Students

Arnaud Bergeron

Master's Research - Université de Montréal

Principal supervisor :

Nicolas Le Roux

arnaud.bergeron1@mila.quebec

Ximeng Mao

PhD - Université de Montréal

Principal supervisor :

Guillaume Lajoie

ximeng.mao@mila.quebec

Collaborating Alumni - McGill University

wabarthm@mila.quebec

Publications

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

Joelle Pineau

Philippe Vincent-Lamarre

Koustuv Sinha

Vincent Larivière

Alina Beygelzimer

Florence d'Alché-Buc

Emily Fox

Hugo Larochelle

One of the challenges in machine learning research is to ensure that presented and published results are sound and reliable. Reproducibility… (see more), that is obtaining similar results as presented in a paper or talk, using the same code and data (when available), is a necessary step to verify the reliability of research findings. Reproducibility is also an important step to promote open and accessible research, thereby allowing the scientific community to quickly integrate new findings and convert ideas to practice. Reproducibility also promotes the use of robust experimental workflows, which potentially reduce unintentional errors. In 2019, the Neural Information Processing Systems (NeurIPS) conference, the premier international conference for research in machine learning, introduced a reproducibility program, designed to improve the standards across the community for how we conduct, communicate, and evaluate machine learning research. The program contained three components: a code submission policy, a community-wide reproducibility challenge, and the inclusion of the Machine Learning Reproducibility checklist as part of the paper submission process. In this paper, we describe each of these components, how it was deployed, as well as what we were able to learn from this initiative.

2020-12-31

Journal of Machine Learning Research (published)

doi.org

arxiv.org

A Simple and Effective Model for Multi-Hop Question Generation

Jimmy Lei Ba

Jamie Ryan Kiros

Geoffrey E Hin-602

Peter W. Battaglia

Jessica Blake

Chandler Hamrick

Vic-613 tor Bapst

Alvaro Sanchez

Vinicius Zambaldi

M. Malinowski

Andrea Tacchetti

David Raposo

Tom B. Brown

Benjamin Mann

Nick Ryder

Melanie Subbiah

Jared Kaplan

Prafulla Dhariwal

Arvind Neelakantan

Pranav Shyam … (see 72 more)

Girish Sastry

William L. Hamilton

Clutrr

Nitish Srivastava

Geoffrey Hinton

Alex Krizhevsky

Ilya Sutskever

Ruslan Salakhutdinov. 2014

Gabriel Stanovsky

Julian Michael

Luke Zettlemoyer

Dan Su

Yan Xu

Wenliang Dai

Ziwei Ji

Tiezheng Yu

Minghao Tu

Kevin Huang

Guangtao Wang

Jing Huang

Ashish Vaswani

Noam M. Shazeer

Niki Parmar

Jakob Uszkoreit

Llion Jones

Aidan N. Gomez

Łukasz Kaiser

Illia Polosukhin. 2017

Attention

Petar Veliˇckovi´c

Guillem Cucurull

Arantxa Casanova

Adriana Romero

Pietro Lio’

Yoshua Bengio

Johannes Welbl

Pontus Stenetorp

Yonghui Wu

Mike Schuster

Quoc Zhifeng Chen

Mohammad Le

Wolfgang Norouzi

Macherey

M. Krikun

Yuan Cao

Qin Gao

William W. Cohen

Jianxing Yu

Xiaojun Quan

Qinliang Su

Jian Yin

Yuyu Zhang

Hanjun Dai

Zornitsa Kozareva

Cheng Zhao

Chenyan Xiong

Corby Rosset

Xia

Paul Song

Bennett Saurabh

Tiwary

Yao Zhao

Xiaochuan Ni

Yuanyuan Ding

Qingyu Zhou

Nan Yang

Furu Wei

Chuanqi Tan

Previous research on automated question gen-001 eration has almost exclusively focused on gen-002 erating factoid questions whose answers ca… (see more)n 003 be extracted from a single document. How-004 ever, there is an increasing interest in develop-005 ing systems that are capable of more complex 006 multi-hop question generation (QG), where an-007 swering the question requires reasoning over 008 multiple documents. In this work, we pro-009 pose a simple and effective approach based on 010 the transformer model for multi-hop QG. Our 011 approach consists of specialized input repre-012 sentations, a supporting sentence classiﬁcation 013 objective, and training data weighting. Prior 014 work on multi-hop QG considers the simpli-015 ﬁed setting of shorter documents and also ad-016 vocates the use of entity-based graph struc-017 tures as essential ingredients in model design. 018 On the contrary, we showcase that our model 019 can scale to the challenging setting of longer 020 documents as input, does not rely on graph 021 structures, and substantially outperforms the 022 state-of-the-art approaches as measured by au-023 tomated metrics and human evaluation. 024

2020-12-31

(published)

www.semanticscholar.org

Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization

Christopher Pal

Adversarial Imitation Learning alternates between learning a discriminator -- which tells apart expert's demonstrations from generated ones … (see more)-- and a generator's policy to produce trajectories that can fool this discriminator. This alternated optimization is known to be delicate in practice since it compounds unstable adversarial training with brittle and sample-inefficient reinforcement learning. We propose to remove the burden of the policy optimization steps by leveraging a novel discriminator formulation. Specifically, our discriminator is explicitly conditioned on two policies: the one from the previous generator's iteration and a learnable policy. When optimized, this discriminator directly learns the optimal generator's policy. Consequently, our discriminator's update solves the generator's optimization problem for free: learning a policy that imitates the expert does not require an additional optimization loop. This formulation effectively cuts by half the implementation and computational burden of Adversarial Imitation Learning algorithms by removing the Reinforcement Learning phase altogether. We show on a variety of tasks that our simpler approach is competitive to prevalent Imitation Learning methods.

2020-12-06

Conference on Neural Information Processing Systems (Accept (poster))

doi.org

arxiv.org

Intervention Design for Effective Sim2Real Transfer

Melissa Mozian

Amy Zhang

Joelle Pineau

David Meger

The goal of this work is to address the recent success of domain randomization and data augmentation for the sim2real setting. We explain th… (see more)is success through the lens of causal inference, positioning domain randomization and data augmentation as interventions on the environment which encourage invariance to irrelevant features. Such interventions include visual perturbations that have no effect on reward and dynamics. This encourages the learning algorithm to be robust to these types of variations and learn to attend to the true causal mechanisms for solving the task. This connection leads to two key findings: (1) perturbations to the environment do not have to be realistic, but merely show variation along dimensions that also vary in the real world, and (2) use of an explicit invariance-inducing objective improves generalization in sim2sim and sim2real transfer settings over just data augmentation or domain randomization alone. We demonstrate the capability of our method by performing zero-shot transfer of a robot arm reach task on a 7DoF Jaco arm learning from pixel observations.

2020-12-02

ArXiv (preprint)

arxiv.org

Interference and Generalization in Temporal Difference Learning

Emmanuel Bengio

Joelle Pineau

Doina Precup

We study the link between generalization and interference in temporal-difference (TD) learning. Interference is defined as the inner product… (see more) of two different gradients, representing their alignment. This quantity emerges as being of interest from a variety of observations about neural networks, parameter sharing and the dynamics of learning. We find that TD easily leads to low-interference, under-generalizing parameters, while the effect seems reversed in supervised learning. We hypothesize that the cause can be traced back to the interplay between the dynamics of interference and bootstrapping. This is supported empirically by several observations: the negative relationship between the generalization gap and interference in TD, the negative effect of bootstrapping on interference and the local coherence of targets, and the contrast between the propagation rate of information in TD(0) versus TD(

2020-11-20

Proceedings of the 37th International Conference on Machine Learning (published)

doi.org

proceedings.mlr.press

Invariant Causal Prediction for Block MDPS

Amy Zhang

Clare Lyle

Shagun Sodhani

Angelos Filos

Marta Kwiatkowska

Joelle Pineau

Yarin Gal

Doina Precup

Generalization across environments is critical to the successful application of reinforcement learning algorithms to real-world challenges. … (see more)In this paper, we consider the problem of learning abstractions that generalize in block MDPs, families of environments with a shared latent state space and dynamics structure over that latent space, but varying observations. We leverage tools from causal inference to propose a method of invariant prediction to learn model-irrelevance state abstractions (MISA) that generalize to novel observations in the multi-environment setting. We prove that for certain classes of environments, this approach outputs with high probability a state abstraction corresponding to the causal feature set with respect to the return. We further provide more general bounds on model error and generalization error in the multi-environment setting, in the process showing a connection between causal variable selection and the state abstraction framework for MDPs. We give empirical evidence that our methods work in both linear and nonlinear settings, attaining improved generalization over single- and multi-task baselines.

2020-11-20

Proceedings of the 37th International Conference on Machine Learning (published)

doi.org

proceedings.mlr.press

The Bottleneck Simulator: A Model-based Deep Reinforcement Learning Approach

Iulian Vlad Serban

Chinnadhurai Sankar

Michael Pieper

Joelle Pineau

Yoshua Bengio

Deep reinforcement learning has recently shown many impressive successes. However, one major obstacle towards applying such methods to real-… (see more)world problems is their lack of data-efficiency. To this end, we propose the Bottleneck Simulator: a model-based reinforcement learning method which combines a learned, factorized transition model of the environment with rollout simulations to learn an effective policy from few examples. The learned transition model employs an abstract, discrete (bottleneck) state, which increases sample efficiency by reducing the number of model parameters and by exploiting structural properties of the environment. We provide a mathematical analysis of the Bottleneck Simulator in terms of fixed points of the learned policy, which reveals how performance is affected by four distinct sources of error: an error related to the abstract space structure, an error related to the transition model estimation variance, an error related to the transition model estimation bias, and an error related to the transition model class bias. Finally, we evaluate the Bottleneck Simulator on two natural language processing tasks: a text adventure game and a real-world, complex dialogue response selection task. On both tasks, the Bottleneck Simulator yields excellent performance beating competing approaches.

2020-10-26

Journal of Artificial Intelligence Research (published)

doi.org

arxiv.org

Randomized Value Functions via Multiplicative Normalizing Flows

Randomized value functions offer a promising approach towards the challenge of efficient exploration in complex environments with high dimen… (see more)sional state and action spaces. Unlike traditional point estimate methods, randomized value functions maintain a posterior distribution over action-space values. This prevents the agent's behavior policy from prematurely exploiting early estimates and falling into local optima. In this work, we leverage recent advances in variational Bayesian neural networks and combine these with traditional Deep Q-Networks (DQN) and Deep Deterministic Policy Gradient (DDPG) to achieve randomized value functions for high-dimensional domains. In particular, we augment DQN and DDPG with multiplicative normalizing flows in order to track a rich approximate posterior distribution over the parameters of the value function. This allows the agent to perform approximate Thompson sampling in a computationally efficient manner via stochastic gradient methods. We demonstrate the benefits of our approach through an empirical comparison in high dimensional environments.

2020-08-05

Conference on Uncertainty in Artificial Intelligence (published)

doi.org

proceedings.mlr.press

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

Multi-task reinforcement learning is a rich paradigm where information from previously seen environments can be leveraged for better perform… (see more)ance and improved sample-efficiency in new environments. In this work, we leverage ideas of common structure underlying a family of Markov decision processes (MDPs) to improve performance in the few-shot regime. We use assumptions of structure from Hidden-Parameter MDPs and Block MDPs to propose a new framework, HiP-BMDP, and approach for learning a common representation and universal dynamics model. To this end, we provide transfer and generalization bounds based on task and state similarity, along with sample complexity bounds that depend on the aggregate number of samples across tasks, rather than the number of tasks, a significant improvement over prior work. To demonstrate the efficacy of the proposed method, we empirically compare and show improvements against other multi-task and meta-reinforcement learning baselines.

2020-07-13

ArXiv (preprint)

arxiv.org

Handling Black Swan Events in Deep Learning with Diversely Extrapolated Neural Networks

Maxime Wabartha

Audrey Durand

Vincent François-Lavet

Joelle Pineau

By virtue of their expressive power, neural networks (NNs) are well suited to fitting large, complex datasets, yet they are also known to … (see more)produce similar predictions for points outside the training distribution. As such, they are, like humans, under the influence of the Black Swan theory: models tend to be extremely "surprised" by rare events, leading to potentially disastrous consequences, while justifying these same events in hindsight. To avoid this pitfall, we introduce DENN, an ensemble approach building a set of Diversely Extrapolated Neural Networks that fits the training data and is able to generalize more diversely when extrapolating to novel data points. This leads DENN to output highly uncertain predictions for unexpected inputs. We achieve this by adding a diversity term in the loss function used to train the model, computed at specific inputs. We first illustrate the usefulness of the method on a low-dimensional regression problem. Then, we show how the loss can be adapted to tackle anomaly detection during classification, as well as safe imitation learning problems.

2020-07-10

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (published)

doi.org

On Overfitting and Asymptotic Bias in Batch Reinforcement Learning with Partial Observability (Extended Abstract)

Vincent François-Lavet

Guillaume Rabusseau

Joelle Pineau

Damien Ernst

Raphael Fonteneau

When an agent has limited information on its environment, the suboptimality of an RL algorithm can be decomposed into the sum of two terms: … (see more)a term related to an asymptotic bias (suboptimality with unlimited data) and a term due to overfitting (additional suboptimality due to limited data). In the context of reinforcement learning with partial observability, this paper provides an analysis of the tradeoff between these two error sources. In particular, our theoretical analysis formally characterizes how a smaller state representation increases the asymptotic bias while decreasing the risk of overfitting.

2020-07-10

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (published)

doi.org

Deep interpretability for GWAS

Deepak Sharma

Audrey Durand

Marc-Andr Legault

Louis-Philippe Lemieux Perreault

Audrey Lemaon

Marie-Pierre Dub

Joelle Pineau

Genome-Wide Association Studies are typically conducted using linear models to find genetic variants associated with common diseases. In the… (see more)se studies, association testing is done on a variant-by-variant basis, possibly missing out on non-linear interaction effects between variants. Deep networks can be used to model these interactions, but they are difficult to train and interpret on large genetic datasets. We propose a method that uses the gradient based deep interpretability technique named DeepLIFT to show that known diabetes genetic risk factors can be identified using deep models along with possibly novel associations.

2020-07-02

arXiv (Cornell University) (preprint)

doi.org

arxiv.org

AI Policy Compass

Mila Ventures Launchpad

Virtual Information Sessions

Joelle Pineau

Biography

Current Students

Publications

AI Policy Compass

Mila Ventures Launchpad

Virtual Information Sessions

Popular keywords:

Joelle Pineau

Biography

Current Students

Publications