Doina Precup

Franco Del Balso

Stagiaire de recherche - UdeM

Mohammad Sami Nur Islam Islam

Manuel Del Verme

Doctorat - McGill

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

Maîtrise recherche - UdeM

Superviseur⋅e principal⋅e :

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

Girdhar Neil Girdhar

Collaborateur·rice de 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

Baccalauréat - McGill

Co-superviseur⋅e :

Gregory Dudek

Zijing Wu

Collaborateur·rice de recherche - 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

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

par

Mingde Harry Zhao

Safa Alver

Harm van Seijen

Romain Laroche

Doina Precup

Yoshua Bengio

Lire l'article

Publications

Learning domain-invariant classifiers for infant cry sounds

Charles Onu

Hemanth K. Sheetha

Arsenii Gorin

2023-11-30

ArXiv (prépublication)

arxiv.org

MUDiff: Unified Diffusion for Complete Molecule Generation

Chenqing Hua

Sitao Luan

Minkai Xu

Zhitao Ying

Rex Ying

Jie Fu

Stefano Ermon

2023-11-18

logconference.io/LOG/2023/Conference (poster)

DGFN: Double Generative Flow Networks

Elaine Lau

Nikhil Murali Vemgal

Emmanuel Bengio

2023-10-27

NeurIPS.cc/2023/Workshop/GenBio (poster)

Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search

Abbas Mehrabian

Ankit Anand

Hyunjik Kim

Nicolas Sonnerat

Matej Balog

Gheorghe Comanici

Tudor Berariu

Andrew Lee

Anian Ruoss

Anna Bulanova

Daniel Toyama

Sam Blackwell

Bernardino Romera Paredes

Petar Veličković

Laurent Orseau

Joonkyung Lee

Anurag Murty Naredla

Adam Zsolt Wagner

2023-10-27

NeurIPS.cc/2023/Workshop/MATH-AI (poster)

Forecaster: Towards Temporally Abstract Tree-Search Planning from Pixels

Thomas Jiralerspong

Flemming Kondrup

Khimya Khetarpal

The ability to plan at many different levels of abstraction enables agents to envision the long-term repercussions of their decisions and th… (voir plus)us enables sample-efficient learning. This becomes particularly beneficial in complex environments from high-dimensional state space such as pixels, where the goal is distant and the reward sparse. We introduce Forecaster, a deep hierarchical reinforcement learning approach which plans over high-level goals leveraging a temporally abstract world model. Forecaster learns an abstract model of its environment by modelling the transitions dynamics at an abstract level and training a world model on such transition. It then uses this world model to choose optimal high-level goals through a tree-search planning procedure. It additionally trains a low-level policy that learns to reach those goals. Our method not only captures building world models with longer horizons, but also, planning with such models in downstream tasks. We empirically demonstrate Forecaster's potential in both single-task learning and generalization to new tasks in the AntMaze domain.

2023-10-27

NeurIPS.cc/2023/Workshop/GenPlan (publié)

A cry for help: Early detection of brain injury in newborns

Charles Onu

Samantha Latremouille

Arsenii Gorin

Junhao Wang

Uchenna Ekwochi

P. Ubuane

O. Kehinde

Muhammad A. Salisu

Datonye Briggs

Yoshua Bengio

2023-10-12

ArXiv (prépublication)

arxiv.org

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)

arxiv.org

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)