Portrait of Doina Precup

Doina Precup

Core Academic Member
Canada CIFAR AI Chair
Associate Professor, McGill University, School of Computer Science
Research Team Leader, Google DeepMind

Biography

Doina Precup combines teaching at McGill University with fundamental research on reinforcement learning, in particular AI applications in areas of significant social impact, such as health care. She is interested in machine decision-making in situations where uncertainty is high.

In addition to heading the Montreal office of Google DeepMind, Precup is a Senior Fellow of the Canadian Institute for Advanced Research and a Fellow of the Association for the Advancement of Artificial Intelligence.

Her areas of speciality are artificial intelligence, machine learning, reinforcement learning, reasoning and planning under uncertainty, and applications.

Current Students

Master's Research - McGill University
Co-supervisor :
PhD - McGill University
Master's Research - McGill University
Postdoctorate - McGill University
Master's Research - McGill University
Research Intern - McGill University
PhD - McGill University
Postdoctorate - Université de Montréal
Principal supervisor :
PhD - McGill University
Master's Research - McGill University
Principal supervisor :
Research Intern - McGill University
PhD - McGill University
Principal supervisor :
Master's Research - McGill University
Co-supervisor :
PhD - McGill University
Co-supervisor :
PhD - McGill University
PhD - McGill University
Co-supervisor :
Research Intern - McGill University
PhD - McGill University
Principal supervisor :
Collaborating researcher - McGill University
Master's Research - McGill University
Master's Research - Université de Montréal
PhD - McGill University
Co-supervisor :
PhD - McGill University
PhD - McGill University
Co-supervisor :
Collaborating researcher - McGill University
Principal supervisor :
PhD - McGill University
Undergraduate - McGill University
Master's Research - Université de Montréal
Principal supervisor :
PhD - McGill University
PhD - McGill University
Principal supervisor :
PhD - McGill University
Principal supervisor :

Publications

Temporally Abstract Partial Models
Zafarali Ahmed
Gheorghe Comanici
Humans and animals have the ability to reason and make predictions about different courses of action at many time scales. In reinforcement l… (see more)earning, option models (Sutton, Precup \& Singh, 1999; Precup, 2000) provide the framework for this kind of temporally abstract prediction and reasoning. Natural intelligent agents are also able to focus their attention on courses of action that are relevant or feasible in a given situation, sometimes termed affordable actions. In this paper, we define a notion of affordances for options, and develop temporally abstract partial option models, that take into account the fact that an option might be affordable only in certain situations. We analyze the trade-offs between estimation and approximation error in planning and learning when using such models, and identify some interesting special cases. Additionally, we empirically demonstrate the ability to learn both affordances and partial option models online resulting in improved sample efficiency and planning time in the Taxi domain.
Phylogenetic Manifold Regularization: A semi-supervised approach to predict transcription factor binding sites
Faizy Ahsan
François Laviolette
The computational prediction of transcription factor binding sites remains a challenging problems in bioinformatics, despite significant met… (see more)hodological developments from the field of machine learning. Such computational models are essential to help interpret the non-coding portion of human genomes, and to learn more about the regulatory mechanisms controlling gene expression. In parallel, massive genome sequencing efforts have produced assembled genomes for hundred of vertebrate species, but this data is underused. We present PhyloReg, a new semi-supervised learning approach that can be used for a wide variety of sequence-to-function prediction problems, and that takes advantage of hundreds of millions of years of evolution to regularize predictors and improve accuracy. We demonstrate that PhyloReg can be used to better train a previously proposed deep learning model of transcription factor binding. Simulation studies further help delineate the benefits of the a pproach. G ains in prediction accuracy are obtained over a broad set of transcription factors and cell types.
What can I do here? A Theory of Affordances in Reinforcement Learning
Zafarali Ahmed
Gheorghe Comanici
David Abel
Efficient Planning under Partial Observability with Unnormalized Q Functions and Spectral Learning
Tianyu Li
Bogdan Mazoure
Value Preserving State-Action Abstractions
David Abel
Nathan Umbanhowar
Dilip Arumugam
Michael L. Littman
Abstraction can improve the sample efficiency of reinforcement learning. However, the process of abstraction inherently discards information… (see more), potentially compromising an agent’s ability to represent high-value policies. To mitigate this, we here introduce combinations of state abstractions and options that are guaranteed to preserve the representation of near-optimal policies. We first define φ-relative options, a general formalism for analyzing the value loss of options paired with a state abstraction, and present necessary and sufficient conditions for φ-relative options to preserve near-optimal behavior in any finite Markov Decision Process. We further show that, under appropriate assumptions, φ-relative options can be composed to induce hierarchical abstractions that are also guaranteed to represent high-value policies.ion can improve the sample efficiency of reinforcement learning. However, the process of abstraction inherently discards information, potentially compromising an agent’s ability to represent high-value policies. To mitigate this, we here introduce combinations of state abstractions and options that are guaranteed to preserve the representation of near-optimal policies. We first define φ-relative options, a general formalism for analyzing the value loss of options paired with a state abstraction, and present necessary and sufficient conditions for φ-relative options to preserve near-optimal behavior in any finite Markov Decision Process. We further show that, under appropriate assumptions, φ-relative options can be composed to induce hierarchical abstractions that are also guaranteed to represent high-value policies.
Value Preserving State-Action Abstractions
David Abel
Nathan Umbanhowar
Dilip Arumugam
Michael L. Littman
Abstraction can improve the sample efficiency of reinforcement learning. However, the process of abstraction inherently discards information… (see more), potentially compromising an agent’s ability to represent high-value policies. To mitigate this, we here introduce combinations of state abstractions and options that are guaranteed to preserve the representation of near-optimal policies. We first define φ-relative options, a general formalism for analyzing the value loss of options paired with a state abstraction, and present necessary and sufficient conditions for φ-relative options to preserve near-optimal behavior in any finite Markov Decision Process. We further show that, under appropriate assumptions, φ-relative options can be composed to induce hierarchical abstractions that are also guaranteed to represent high-value policies.ion can improve the sample efficiency of reinforcement learning. However, the process of abstraction inherently discards information, potentially compromising an agent’s ability to represent high-value policies. To mitigate this, we here introduce combinations of state abstractions and options that are guaranteed to preserve the representation of near-optimal policies. We first define φ-relative options, a general formalism for analyzing the value loss of options paired with a state abstraction, and present necessary and sufficient conditions for φ-relative options to preserve near-optimal behavior in any finite Markov Decision Process. We further show that, under appropriate assumptions, φ-relative options can be composed to induce hierarchical abstractions that are also guaranteed to represent high-value policies.
Options of Interest: Temporal Abstraction with Interest Functions
Martin Klissarov
Maxime Chevalier-Boisvert
Temporal abstraction refers to the ability of an agent to use behaviours of controllers which act for a limited, variable amount of time. Th… (see more)e options framework describes such behaviours as consisting of a subset of states in which they can initiate, an internal policy and a stochastic termination condition. However, much of the subsequent work on option discovery has ignored the initiation set, because of difficulty in learning it from data. We provide a generalization of initiation sets suitable for general function approximation, by defining an interest function associated with an option. We derive a gradient-based learning algorithm for interest functions, leading to a new interest-option-critic architecture. We investigate how interest functions can be leveraged to learn interpretable and reusable temporal abstractions. We demonstrate the efficacy of the proposed approach through quantitative and qualitative results, in both discrete and continuous environments.
A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms
We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We demonstrate it… (see more)s effectiveness by presenting simple and unified proofs of convergence for a variety of commonly-used methods. We show that value-based methods such as TD(
Provably efficient reconstruction of policy networks
Recent research has shown that learning poli-cies parametrized by large neural networks can achieve significant success on challenging reinf… (see more)orcement learning problems. However, when memory is limited, it is not always possible to store such models exactly for inference, and com-pressing the policy into a compact representation might be necessary. We propose a general framework for policy representation, which reduces this problem to finding a low-dimensional embedding of a given density function in a separable inner product space. Our framework allows us to de-rive strong theoretical guarantees, controlling the error of the reconstructed policies. Such guaran-tees are typically lacking in black-box models, but are very desirable in risk-sensitive tasks. Our experimental results suggest that the reconstructed policies can use less than 10%of the number of parameters in the original networks, while incurring almost no decrease in rewards.
Representation of Reinforcement Learning Policies in Reproducing Kernel Hilbert Spaces.
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.
A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms
Efficient Planning under Partial Observability with Unnormalized Q Functions and Spectral Learning
Tianyu Li
Bogdan Mazoure
Learning and planning in partially-observable domains is one of the most difficult problems in reinforcement learning. Traditional methods c… (see more)onsider these two problems as independent, resulting in a classical two-stage paradigm: first learn the environment dynamics and then plan accordingly. This approach, however, disconnects the two problems and can consequently lead to algorithms that are sample inefficient and time consuming. In this paper, we propose a novel algorithm that combines learning and planning together. Our algorithm is closely related to the spectral learning algorithm for predicitive state representations and offers appealing theoretical guarantees and time complexity. We empirically show on two domains that our approach is more sample and time efficient compared to classical methods.