Doina Precup

Mohammad Sami Nur Islam Islam

Jesse Farebrother

Doctorat - McGill

Superviseur⋅e principal⋅e :

Marc Gendron-Bellemare

Doctorat - McGill

Superviseur⋅e principal⋅e :

Eilif Benjamin Muller

Doctorat - McGill

Doctorat - McGill

Maîtrise recherche - McGill

Arushi Jain

Doctorat - McGill

Doctorat - McGill

Postdoctorat - McGill

Elaine Lau

Maîtrise recherche - McGill

Jonathan Lebensold

Collaborateur·rice alumni - McGill

Site web

Ray Luo

Doctorat - McGill

Superviseur⋅e principal⋅e :

G McCracken

Doctorat - McGill

Nazanin Mohammadi Sepahvand

Doctorat - McGill

Shahrad Mohammadzadeh

Maîtrise recherche - McGill

Superviseur⋅e principal⋅e :

Gabriela Moisescu-Pareja

Maîtrise recherche - McGill

Padideh Nouri

Doctorat - UdeM

Co-superviseur⋅e :

Charles Onu

Doctorat - McGill

Doctorat - McGill

Co-superviseur⋅e :

Nate Rahn

Doctorat - McGill

Superviseur⋅e principal⋅e :

Marc Gendron-Bellemare

Sahand Rezaei-Shoshtari

Doctorat - McGill

Co-superviseur⋅e :

Doctorat - McGill

Co-superviseur⋅e :

Doctorat - McGill

Co-superviseur⋅e :

Blake Richards

samiemandana@gmail.com

Doctorat - McGill

Nishanth Anand Vemgal

Doctorat - McGill

Doctorat - McGill

Doctorat - McGill

Co-superviseur⋅e :

Samira Ebrahimi Kahou

Stagiaire de recherche - McGill

Steve Wen

Maîtrise recherche - McGill

Co-superviseur⋅e :

Gregory Dudek

Skipper : combiner l’abstraction spatiale et temporelle afin d’améliorer la généralisation

Zijing Wu

Doctorat - McGill

Co-superviseur⋅e :

Doctorat - McGill

Harry Zhao

Doctorat - McGill

Co-superviseur⋅e :

Billets de blogue

Generic thumbnail for Mila Blog articles.

22 février 2024

par

Mingde Harry Zhao

Safa Alver

Harm van Seijen

Romain Laroche

Doina Precup

Yoshua Bengio

Lire l'article

Publications

Hybrid Scattering Transform - Long Short-Term Memory Networks for Intrapartum Fetal Heart Rate Classification

"Derek Kweku DEGBEDZUI

Michael W Kuzniewicz

Marie-Coralie Cornet

Yvonne Wu

Heather Forquer

Lawrence Gerstley

Emily F. Hamilton

P. Warrick

Robert E. Kearney

This study assessed the early detection of the increased risk of hypoxic ischemic encephalopathy using raw fetal heart rate and its transfor… (voir plus)mation with scattering transform and a long short-term memory recurrent neural network. There was no significant difference between the two approaches. However, the use of scattering transform produced lower computational demands. Considering scalability to the large data in our database and computational efficiency, the experiments involving scattering transform coefficients will be selected to conduct subsequent experiments. Future works will address the limitations of this study, including the low model performance.

2023-10-01

2023 Computing in Cardiology (CinC) (publié)

A Definition of Continual Reinforcement Learning

David Abel

Andre Barreto

Benjamin Van Roy

Hado van Hasselt

Satinder Singh

For SALE: State-Action Representation Learning for Deep Reinforcement Learning

Scott Fujimoto

Wei-Di Chang

Edward J. Smith

Shixiang Shane Gu

David Meger

In the field of reinforcement learning (RL), representation learning is a proven tool for complex image-based tasks, but is often overlooked… (voir plus) for environments with low-level states, such as physical control problems. This paper introduces SALE, a novel approach for learning embeddings that model the nuanced interaction between state and action, enabling effective representation learning from low-level states. We extensively study the design space of these embeddings and highlight important design considerations. We integrate SALE and an adaptation of checkpoints for RL into TD3 to form the TD7 algorithm, which significantly outperforms existing continuous control algorithms. On OpenAI gym benchmark tasks, TD7 has an average performance gain of 276.7% and 50.7% over TD3 at 300k and 5M time steps, respectively, and works in both the online and offline settings.

Prediction and Control in Continual Reinforcement Learning

Nishanth Anand

Temporal difference (TD) learning is often used to update the estimate of the value function which is used by RL agents to extract useful po… (voir plus)licies. In this paper, we focus on value function estimation in continual reinforcement learning. We propose to decompose the value function into two components which update at different timescales: a _permanent_ value function, which holds general knowledge that persists over time, and a _transient_ value function, which allows quick adaptation to new situations. We establish theoretical results showing that our approach is well suited for continual learning and draw connections to the complementary learning systems (CLS) theory from neuroscience. Empirically, this approach improves performance significantly on both prediction and control problems.

Policy composition in reinforcement learning via multi-objective policy optimization

Shruti Mishra

Ankit Anand

Jordan Hoffmann

Nicolas Heess

Martin A. Riedmiller

Abbas Abdolmaleki

We enable reinforcement learning agents to learn successful behavior policies by utilizing relevant pre-existing teacher policies. The teach… (voir plus)er policies are introduced as objectives, in addition to the task objective, in a multi-objective policy optimization setting. Using the Multi-Objective Maximum a Posteriori Policy Optimization algorithm (Abdolmaleki et al. 2020), we show that teacher policies can help speed up learning, particularly in the absence of shaping rewards. In two domains with continuous observation and action spaces, our agents successfully compose teacher policies in sequence and in parallel, and are also able to further extend the policies of the teachers in order to solve the task. Depending on the specified combination of task and teacher(s), teacher(s) may naturally act to limit the final performance of an agent. The extent to which agents are required to adhere to teacher policies are determined by hyperparameters which determine both the effect of teachers on learning speed and the eventual performance of the agent on the task. In the humanoid domain (Tassa et al. 2018), we also equip agents with the ability to control the selection of teachers. With this ability, agents are able to meaningfully compose from the teacher policies to achieve a superior task reward on the walk task than in cases without access to the teacher policies. We show the resemblance of composed task policies with the corresponding teacher policies through videos.

2023-08-29

ArXiv (prépublication)

Acceleration in Policy Optimization

Veronica Chelu

Tom Zahavy

Arthur Guez

Sebastian Flennerhag

We work towards a unifying paradigm for accelerating policy optimization methods in reinforcement learning (RL) through predictive and adapt… (voir plus)ive directions of (functional) policy ascent. Leveraging the connection between policy iteration and policy gradient methods, we view policy optimization algorithms as iteratively solving a sequence of surrogate objectives, local lower bounds on the original objective. We define optimism as predictive modelling of the future behavior of a policy, and hindsight adaptation as taking immediate and anticipatory corrective actions to mitigate accumulating errors from overshooting predictions or delayed responses to change. We use this shared lens to jointly express other well-known algorithms, including model-based policy improvement based on forward search, and optimistic meta-learning algorithms. We show connections with Anderson acceleration, Nesterov's accelerated gradient, extra-gradient methods, and linear extrapolation in the update rule. We analyze properties of the formulation, design an optimistic policy gradient algorithm, adaptive via meta-gradient learning, and empirically highlight several design choices pertaining to acceleration, in an illustrative task.

2023-07-20

EWRL/2023/Workshop (accepté)

On the Convergence of Bounded Agents

David Abel

Andre Barreto

Hado Philip van Hasselt

Benjamin Van Roy

Satinder Singh

When has an agent converged? Standard models of the reinforcement learning problem give rise to a straightforward definition of convergence:… (voir plus) An agent converges when its behavior or performance in each environment state stops changing. However, as we shift the focus of our learning problem from the environment's state to the agent's state, the concept of an agent's convergence becomes significantly less clear. In this paper, we propose two complementary accounts of agent convergence in a framing of the reinforcement learning problem that centers around bounded agents. The first view says that a bounded agent has converged when the minimal number of states needed to describe the agent's future behavior cannot decrease. The second view says that a bounded agent has converged just when the agent's performance only changes if the agent's internal state changes. We establish basic properties of these two definitions, show that they accommodate typical views of convergence in standard settings, and prove several facts about their nature and relationship. We take these perspectives, definitions, and analysis to bring clarity to a central idea of the field.

2023-07-20

ArXiv (prépublication)

Accelerating exploration and representation learning with offline pre-training

Bogdan Mazoure

Jake Bruce

Rob Fergus

Ankit Anand

Sequential decision-making agents struggle with long horizon tasks, since solving them requires multi-step reasoning. Most reinforcement lea… (voir plus)rning (RL) algorithms address this challenge by improved credit assignment, introducing memory capability, altering the agent's intrinsic motivation (i.e. exploration) or its worldview (i.e. knowledge representation). Many of these components could be learned from offline data. In this work, we follow the hypothesis that exploration and representation learning can be improved by separately learning two different models from a single offline dataset. We show that learning a state representation using noise-contrastive estimation and a model of auxiliary reward separately from a single collection of human demonstrations can significantly improve the sample efficiency on the challenging NetHack benchmark. We also ablate various components of our experimental setting and highlight crucial insights.

2023-06-20

ICML.cc/2023/Workshop/ILHF (publié)

An Empirical Study of the Effectiveness of Using a Replay Buffer on Mode Discovery in GFlowNets

Nikhil Murali Vemgal

Elaine Lau

Reinforcement Learning (RL) algorithms aim to learn an optimal policy by iteratively sampling actions to learn how to maximize the total exp… (voir plus)ected return,

2023-06-19

ICML.cc/2023/Workshop/SPIGM (poster)

When Do Graph Neural Networks Help with Node Classification? Investigating the Impact of Homophily Principle on Node Distinguishability

Sitao Luan

Chenqing Hua

Minkai Xu

Qincheng Lu

Jiaqi Zhu

Xiao-Wen Chang

Jie Fu

Jure Leskovec

2023-04-25

ArXiv (prépublication)

Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation

Gandharv Patil

Prashanth L.A.

Dheeraj M. Nagaraj

We study the finite-time behaviour of the popular temporal difference (TD) learning algorithm, when combined with tail-averaging. We derive … (voir plus)finite time bounds on the parameter error of the tail-averaged TD iterate under a step-size choice that does not require information about the eigenvalues of the matrix underlying the projected TD fixed point. Our analysis shows that tail-averaged TD converges at the optimal O (1/t) rate, both in expectation and with high probability. In addition, our bounds exhibit a sharper rate of decay for the initial error (bias), which is an improvement over averaging all iterates. We also propose and analyse a variant of TD that incorporates regularisation, and show that this variant fares favourably in problems with ill-conditioned features.

2023-04-11

Proceedings of The 26th International Conference on Artificial Intelligence and Statistics (publié)

The Stable Entropy Hypothesis and Entropy-Aware Decoding: An Analysis and Algorithm for Robust Natural Language Generation

Kushal Arora

Timothy O'Donnell

Jason Aaron Edward Weston

Jackie C.K.Cheung

State-of-the-art language generation models can degenerate when applied to open-ended generation problems such as text completion, story gen… (voir plus)eration, or dialog modeling. This degeneration usually shows up in the form of incoherence, lack of vocabulary diversity, and self-repetition or copying from the context. In this paper, we postulate that ``human-like'' generations usually lie in a narrow and nearly flat entropy band, and violation of these entropy bounds correlates with degenerate behavior. Our experiments show that this stable narrow entropy zone exists across models, tasks, and domains and confirm the hypothesis that violations of this zone correlate with degeneration. We then use this insight to propose an entropy-aware decoding algorithm that respects these entropy bounds resulting in less degenerate, more contextual, and"human-like"language generation in open-ended text generation settings.

2023-02-14

ArXiv (prépublication)