Joelle Pineau

Vincent François-Lavet

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.

2020-06-30

International Joint Conference on Artificial Intelligence (published)

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

Vincent François-Lavet

Guillaume Rabusseau

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.

2020-06-30

International Joint Conference on Artificial Intelligence (published)

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

Iulian V. Serban

Varun Gupta

Ekaterina Kochmar

Dung D. Vu

Robert Belfer

2020-06-09

Artificial Intelligence in Education (published)

Leveraging exploration in off-policy algorithms via normalizing flows

Bogdan Mazoure

Thang Doan

R Devon Hjelm

The ability to discover approximately optimal policies in domains with sparse rewards is crucial to applying reinforcement learning (RL) in … (see more)many real-world scenarios. Approaches such as neural density models and continuous exploration (e.g., Go-Explore) have been proposed to maintain the high exploration rate necessary to find high performing and generalizable policies. Soft actor-critic(SAC) is another method for improving exploration that aims to combine efficient learning via off-policy updates while maximizing the policy entropy. In this work, we extend SAC to a richer class of probability distributions (e.g., multimodal) through normalizing flows (NF) and show that this significantly improves performance by accelerating the discovery of good policies while using much smaller policy representations. Our approach, which we call SAC-NF, is a simple, efficient,easy-to-implement modification and improvement to SAC on continuous control baselines such as MuJoCo and PyBullet Roboschool domains. Finally, SAC-NF does this while being significantly parameter efficient, using as few as 5.5% the parameters for an equivalent SAC model.

2020-05-11

Proceedings of the Conference on Robot Learning (published)

proceedings.mlr.press

Literature Mining for Incorporating Inductive Bias in Biomedical Prediction Tasks (Student Abstract)

Qizhen Zhang

2020-04-02

AAAI Conference on Artificial Intelligence (published)

Representation of Reinforcement Learning Policies in Reproducing Kernel Hilbert Spaces

Thang Doan

We propose a general framework for policy representation for reinforcement learning tasks. This framework involves finding a low-dimensional… (see more) embedding of the policy on a reproducing kernel Hilbert space (RKHS). The usage of RKHS based methods allows us to derive strong theoretical guarantees on the expected return of the reconstructed policy. Such guarantees are typically lacking in black-box models, but are very desirable in tasks requiring stability. We conduct several experiments on classic RL domains. The results confirm that the policies can be robustly embedded in a low-dimensional space while the embedded policy incurs almost no decrease in return.

2020-02-06

(published)

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.

2019-12-31

Advances in Neural Information Processing Systems 33 (NeurIPS 2020) (published)

Deep interpretability for GWAS

Deepak Sharma

Marc-Andr Legault

Louis-Philippe Lemieux Perreault

Audrey Lemaon

Marie-Pierre Dub

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.

2019-12-31

arXiv (preprint)

Language Gans Falling Short

Massimo Caccia

Lucas Caccia

William Fedus

Hugo Larochelle

Laurent Charlin

Generating high-quality text with sufficient diversity is essential for a wide range of Natural Language Generation (NLG) tasks. Maximum-Lik… (see more)elihood (MLE) models trained with teacher forcing have consistently been reported as weak baselines, where poor performance is attributed to exposure bias (Bengio et al., 2015; Ranzato et al., 2015); at inference time, the model is fed its own prediction instead of a ground-truth token, which can lead to accumulating errors and poor samples. This line of reasoning has led to an outbreak of adversarial based approaches for NLG, on the account that GANs do not suffer from exposure bias. In this work, we make several surprising observations which contradict common beliefs. First, we revisit the canonical evaluation framework for NLG, and point out fundamental flaws with quality-only evaluation: we show that one can outperform such metrics using a simple, well-known temperature parameter to artificially reduce the entropy of the model's conditional distributions. Second, we leverage the control over the quality / diversity trade-off given by this parameter to evaluate models over the whole quality-diversity spectrum and find MLE models constantly outperform the proposed GAN variants over the whole quality-diversity space. Our results have several implications: 1) The impact of exposure bias on sample quality is less severe than previously thought, 2) temperature tuning provides a better quality / diversity trade-off than adversarial training while being easier to train, easier to cross-validate, and less computationally expensive. Code to reproduce the experiments is available at github.com/pclucas14/GansFallingShort

2019-12-31

ICLR (published)

openreview.net

Deep Generative Modeling of LiDAR Data

Lucas Caccia

Herke van Hoof

Aaron Courville

Building models capable of generating structured output is a key challenge for AI and robotics. While generative models have been explored o… (see more)n many types of data, little work has been done on synthesizing lidar scans, which play a key role in robot mapping and localization. In this work, we show that one can adapt deep generative models for this task by unravelling lidar scans into a 2D point map. Our approach can generate high quality samples, while simultaneously learning a meaningful latent representation of the data. We demonstrate significant improvements against state-of-the-art point cloud generation methods. Furthermore, we propose a novel data representation that augments the 2D signal with absolute positional information. We show that this helps robustness to noisy and imputed input; the learned model can recover the underlying lidar scan from seemingly uninformative data

2019-11-02

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (published)

Assessing Generalization in TD methods for Deep Reinforcement Learning

Emmanuel Bengio

Doina Precup

2019-09-24

(published)

openreview.net

Combined Reinforcement Learning via Abstract Representations

Vincent François-Lavet

Yoshua Bengio

Doina Precup

In the quest for efficient and robust reinforcement learning methods, both model-free and model-based approaches offer advantages. In this p… (see more)aper we propose a new way of explicitly bridging both approaches via a shared low-dimensional learned encoding of the environment, meant to capture summarizing abstractions. We show that the modularity brought by this approach leads to good generalization while being computationally efficient, with planning happening in a smaller latent state space. In addition, this approach recovers a sufficient low-dimensional representation of the environment, which opens up new strategies for interpretable AI, exploration and transfer learning.

2019-07-16

Proceedings of the AAAI Conference on Artificial Intelligence (published)