Portrait de Doina Precup

Doina Precup

Membre académique principal
Chaire en IA Canada-CIFAR
Professeure agrégée, McGill University
Chef d'équipe de recherche, Google DeepMind
Sujets de recherche
Apprentissage automatique médical
Apprentissage par renforcement
Modèles probabilistes
Modélisation moléculaire
Raisonnement

Biographie

Doina Precup enseigne à l'Université McGill tout en menant des recherches fondamentales sur l'apprentissage par renforcement, notamment les applications de l'IA dans des domaines ayant des répercussions sociales, tels que les soins de santé. Elle s'intéresse à la prise de décision automatique dans des situations d'incertitude élevée.

Elle est membre de l'Institut canadien de recherches avancées (CIFAR) et de l'Association pour l'avancement de l'intelligence artificielle (AAAI), et dirige le bureau montréalais de DeepMind.

Ses spécialités sont les suivantes : intelligence artificielle, apprentissage machine, apprentissage par renforcement, raisonnement et planification sous incertitude, applications.

Étudiants actuels

Collaborateur·rice alumni - McGill
Co-superviseur⋅e :
Collaborateur·rice alumni - McGill
Doctorat - McGill
Superviseur⋅e principal⋅e :
Maîtrise recherche - McGill
Superviseur⋅e principal⋅e :
Maîtrise recherche - McGill
Co-superviseur⋅e :
Maîtrise recherche - McGill
Doctorat - McGill
Superviseur⋅e principal⋅e :
Maîtrise recherche - McGill
Doctorat - Polytechnique
Superviseur⋅e principal⋅e :
Visiteur de recherche indépendant - McGill
Co-superviseur⋅e :
Collaborateur·rice alumni - McGill
Doctorat - McGill
Superviseur⋅e principal⋅e :
Maîtrise recherche - McGill
Collaborateur·rice alumni - McGill
Superviseur⋅e principal⋅e :
Doctorat - McGill
Superviseur⋅e principal⋅e :
Stagiaire de recherche - McGill
Maîtrise recherche - McGill
Co-superviseur⋅e :
Stagiaire de recherche - McGill
Doctorat - McGill
Superviseur⋅e principal⋅e :
Collaborateur·rice alumni - McGill
Co-superviseur⋅e :

Publications

Dyna Planning using a Feature Based Generative Model
Ryan Faulkner
Dyna-style reinforcement learning is a powerful approach for problems where not much real data is available. The main idea is to supplement … (voir plus)real trajectories, or sequences of sampled states over time, with simulated ones sampled from a learned model of the environment. However, in large state spaces, the problem of learning a good generative model of the environment has been open so far. We propose to use deep belief networks to learn an environment model for use in Dyna. We present our approach and validate it empirically on problems where the state observations consist of images. Our results demonstrate that using deep belief networks, which are full generative models, significantly outperforms the use of linear expectation models, proposed in Sutton et al. (2008)
Deep Reinforcement Learning that Matters
In recent years, significant progress has been made in solving challenging problems across various domains using deep reinforcement learning… (voir plus) (RL). Reproducing existing work and accurately judging the improvements offered by novel methods is vital to sustaining this progress. Unfortunately, reproducing results for state-of-the-art deep RL methods is seldom straightforward. In particular, non-determinism in standard benchmark environments, combined with variance intrinsic to the methods, can make reported results tough to interpret. Without significance metrics and tighter standardization of experimental reporting, it is difficult to determine whether improvements over the prior state-of-the-art are meaningful. In this paper, we investigate challenges posed by reproducibility, proper experimental techniques, and reporting procedures. We illustrate the variability in reported metrics and results when comparing against common baselines and suggest guidelines to make future results in deep RL more reproducible. We aim to spur discussion about how to ensure continued progress in the field by minimizing wasted effort stemming from results that are non-reproducible and easily misinterpreted.
Imitation Upper Confidence Bound for Bandits on a Graph
We consider a graph of interconnected agents implementing a common policy and each playing a bandit problem with identical reward distributi… (voir plus)ons. We restrict the information propagated in the graph such that agents can uniquely observe each other's actions. We propose an extension of the Upper Confidence Bound (UCB) algorithm to this setting and empirically demonstrate that our solution improves the performance over UCB according to multiple metrics and within various graph configurations.
Learning Predictive State Representations From Non-Uniform Sampling
Yuri Grinberg
Melanie Lyman-Abramovitch
Borja Balle
Predictive state representations (PSR) have emerged as a powerful method for modelling partially observable environments. PSR learning algor… (voir plus)ithms can build models for predicting all observable variables, or predicting only some of them conditioned on others (e.g., actions or exogenous variables). In the latter case, which we call conditional modelling, the accuracy of different estimates of the conditional probabilities for a fixed dataset can vary significantly, due to the limited sampling of certain conditions. This can have negative consequences on the PSR parameter estimation process, which are not taken into account by the current state-of-the-art PSR spectral learning algorithms. In this paper, we examine closely conditional modelling within the PSR framework. We first establish a new positive but surprisingly non-trivial result: a conditional model can never be larger than the complete model. Then, we address the core shortcoming of existing PSR spectral learning methods for conditional models by incorporating an additional step in the process, which can be seen as a type of matrix denoising. We further refine this objective by adding penalty terms for violations of the system dynamics matrix structure, which improves the PSR predictive performance. Empirical evaluations on both synthetic and real datasets highlight the advantages of the proposed approach.
Learning with Options that Terminate Off-Policy
Anna Harutyunyan
Peter Vrancx
Ann Nowé
A temporally abstract action, or an option, is specified by a policy and a termination condition: the policy guides option behavior, and the… (voir plus) termination condition roughly determines its length. Generally, learning with longer options (like learning with multi-step returns) is known to be more efficient. However, if the option set for the task is not ideal, and cannot express the primitive optimal policy exactly, shorter options offer more flexibility and can yield a better solution. Thus, the termination condition puts learning efficiency at odds with solution quality. We propose to resolve this dilemma by decoupling the behavior and target terminations, just like it is done with policies in off-policy learning. To this end, we give a new algorithm, Q(β), that learns the solution with respect to any termination condition, regardless of how the options actually terminate. We derive Q(β) by casting learning with options into a common framework with well-studied multi-step off-policy learning. We validate our algorithm empirically, and show that it holds up to its motivating claims.
OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning
Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward fu… (voir plus)nction can be difficult, especially for intricate tasks. Inverse reinforcement learning offers a useful paradigm to learn the underlying reward function directly from expert demonstrations. Yet in reality, the corpus of demonstrations may contain trajectories arising from a diverse set of underlying reward functions rather than a single one. Thus, in inverse reinforcement learning, it is useful to consider such a decomposition. The options framework in reinforcement learning is specifically designed to decompose policies in a similar light. We therefore extend the options framework and propose a method to simultaneously recover reward options in addition to policy options. We leverage adversarial methods to learn joint reward-policy options using only observed expert states. We show that this approach works well in both simple and complex continuous control tasks and shows significant performance increases in one-shot transfer learning.
When Waiting is not an Option: Learning Options with a Deliberation Cost
Recent work has shown that temporally extended actions (options) can be learned fully end-to-end as opposed to being specified in advance. W… (voir plus)hile the problem of "how" to learn options is increasingly well understood, the question of "what" good options should be has remained elusive. We formulate our answer to what "good" options should be in the bounded rationality framework (Simon, 1957) through the notion of deliberation cost. We then derive practical gradient-based learning algorithms to implement this objective. Our results in the Arcade Learning Environment (ALE) show increased performance and interpretability.
Learning Robust Options
Daniel J. Mankowitz
Timothy A. Mann
Shie Mannor
Robust reinforcement learning aims to produce policies that have strong guarantees even in the face of environments/transition models whose … (voir plus)parameters have strong uncertainty. Existing work uses value-based methods and the usual primitive action setting. In this paper, we propose robust methods for learning temporally abstract actions, in the framework of options. We present a Robust Options Policy Iteration (ROPI) algorithm with convergence guarantees, which learns options that are robust to model uncertainty. We utilize ROPI to learn robust options with the Robust Options Deep Q Network (RO-DQN) that solves multiple tasks and mitigates model misspecification due to model uncertainty. We present experimental results which suggest that policy iteration with linear features may have an inherent form of robustness when using coarse feature representations. In addition, we present experimental results which demonstrate that robustness helps policy iteration implemented on top of deep neural networks to generalize over a much broader range of dynamics than non-robust policy iteration.
Constructing Temporal Abstractions Autonomously in Reinforcement Learning
Patterns of reintubation in extremely preterm infants: a longitudinal cohort study
Wissam Shalish
Lara Kanbar
Martin Keszler
Sanjay Chawla
Lajos Kovacs
Smita Rao
Bogdan A Panaitescu
Alyse Laliberte
Karen Brown
Robert E Kearney
Guilherme M Sant'Anna
Analyzing Alzheimer’s Disease Progression from Sequential Magnetic Resonance Imaging Scans Using Deep 3D Convolutional Neural Networks
Konrad Wagstyl
Azar Zandifar
Adriana Romero
Alzheimer’s is a progressive, neurodegenerative disease, that causes irreversible damage to the brain tissue. It impairs the ability to fo… (voir plus)rm and retrieve memory, and eventually disrupts the natural flow of life, by affecting the ability to carry out even day to day activities. The disease is typically diagnosed from the symptoms (Mini Mental State Examination, [8]), such as decline in cognitive abilities, visual and/or speech impairment, loss of memory, rather than the structural changes in the brain (biomarker) that causes it. But the pathological changes in the brain start decades before the manifestation of the symptoms [7]. Magnetic Resonance Imaging (MRI) is capable of capturing the complex changes in the brain, even if it is difficult for humans to extract those features from the low contrast, multi-dimensional MRIs [1]. There is a considerable amount of work on analyzing Alzheimer’s disease. However, the vast majority intends to predict the state of the disease at the current time step.
Disentangling the independently controllable factors of variation by interacting with the world
It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it rema… (voir plus)ins an open question what kind of training framework could potentially achieve that. Whereas most previous work focuses on the static setting (e.g., with images), we postulate that some of the causal factors could be discovered if the learner is allowed to interact with its environment. The agent can experiment with different actions and observe their effects. More specifically, we hypothesize that some of these factors correspond to aspects of the environment which are independently controllable, i.e., that there exists a policy and a learnable feature for each such aspect of the environment, such that this policy can yield changes in that feature with minimal changes to other features that explain the statistical variations in the observed data. We propose a specific objective function to find such factors, and verify experimentally that it can indeed disentangle independently controllable aspects of the environment without any extrinsic reward signal.