Doina Precup

Sumana Basu

PhD - McGill University

Co-supervisor :

Adriana Romero Soriano

PhD - McGill University

Lynn Cherif

Master's Research - McGill University

Co-supervisor :

PhD - McGill University

Co-supervisor :

PhD - McGill University

Principal supervisor :

David Meger

Jonathan Colaço Carr

Master's Research - McGill University

Principal supervisor :

Prakash Panangaden

Élodie Coté-Gauthier

Collaborating researcher - McGill University

Franco Del Balso

Research Intern - Université de Montréal

Jesse Farebrother

PhD - McGill University

Principal supervisor :

Marc Gendron-Bellemare

PhD - McGill University

Principal supervisor :

Eilif Benjamin Muller

PhD - McGill University

Haque Ishfaq

PhD - McGill University

Mohammad Sami Nur Islam Islam

Master's Research - McGill University

Arushi Jain

PhD - McGill University

PhD - McGill University

Postdoctorate - McGill University

Elaine Lau

Master's Research - McGill University

Jonathan Lebensold

Collaborating Alumni - McGill University

Undergraduate - McGill University

Ray Luo

PhD - McGill University

Principal supervisor :

G McCracken

PhD - McGill University

Nazanin Mohammadi Sepahvand

PhD - McGill University

Shahrad Mohammadzadeh

Master's Research - McGill University

Principal supervisor :

Gabriela Moisescu-Pareja

Collaborating researcher - McGill University

Co-supervisor :

Irina Rish

Padideh Nouri

PhD - Université de Montréal

Co-supervisor :

Charles Onu

PhD - McGill University

PhD - McGill University

Co-supervisor :

Nate Rahn

PhD - McGill University

Principal supervisor :

Marc Gendron-Bellemare

Sahand Rezaei-Shoshtari

PhD - McGill University

Co-supervisor :

PhD - McGill University

Co-supervisor :

PhD - McGill University

Co-supervisor :

Blake Richards

samiemandana@gmail.com

PhD - McGill University

Nishanth Anand Vemgal

PhD - McGill University

PhD - McGill University

Priyesh Vijayan

PhD - McGill University

Co-supervisor :

Samira Ebrahimi Kahou

Zihan Wang

PhD - McGill University

Guangyuan Wang

Research Intern - McGill University

Steve Wen

Master's Research - McGill University

Co-supervisor :

Gregory Dudek

Zijing Wu

PhD - McGill University

Co-supervisor :

PhD - McGill University

Skipper: Combining Spatial and Temporal Abstraction for Better Generalization

Harry Zhao

Collaborating Alumni - McGill University

Co-supervisor :

Blog Posts

Generic thumbnail for Mila Blog articles.

February 22, 2024

Mingde Harry Zhao

Safa Alver

Harm van Seijen

Romain Laroche

Doina Precup

Yoshua Bengio

Read the article

Publications

Agency Is Frame-Dependent

David Abel

Andre Barreto

Michael Bowling

Will Dabney

Shi Dong

Steven Hansen

A. Harutyunyan

Khimya Khetarpal

Clare Lyle

Razvan Pascanu

Georgios Piliouras

Jonathan Richens

Mark Rowland

Tom Schaul

Satinder Singh

Agency is a system's capacity to steer outcomes toward a goal, and is a central topic of study across biology, philosophy, cognitive science… (see more), and artificial intelligence. Determining if a system exhibits agency is a notoriously difficult question: Dennett (1989), for instance, highlights the puzzle of determining which principles can decide whether a rock, a thermostat, or a robot each possess agency. We here address this puzzle from the viewpoint of reinforcement learning by arguing that agency is fundamentally frame-dependent: Any measurement of a system's agency must be made relative to a reference frame. We support this claim by presenting a philosophical argument that each of the essential properties of agency proposed by Barandiaran et al. (2009) and Moreno (2018) are themselves frame-dependent. We conclude that any basic science of agency requires frame-dependence, and discuss the implications of this claim for reinforcement learning.

2025-02-06

ArXiv (preprint)

Agency Is Frame-Dependent

David Abel

Andre Barreto

Michael Bowling

Will Dabney

Shi Dong

Steven Hansen

Anna Harutyunyan

Khimya Khetarpal

Clare Lyle

Razvan Pascanu

Georgios Piliouras

Jonathan Richens

Mark Rowland

Tom Schaul

Satinder Singh

2025-02-06

ArXiv (preprint)

Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning

Haque Ishfaq

Guangyuan Wang

Mohammad Sami Nur Islam

Existing actor-critic algorithms, which are popular for continuous control reinforcement learning (RL) tasks, suffer from poor sample effici… (see more)ency due to lack of principled exploration mechanism within them. Motivated by the success of Thompson sampling for efficient exploration in RL, we propose a novel model-free RL algorithm, Langevin Soft Actor Critic (LSAC), which prioritizes enhancing critic learning through uncertainty estimation over policy optimization. LSAC employs three key innovations: approximate Thompson sampling through distributional Langevin Monte Carlo (LMC) based

2025-01-22

ICLR.cc/2025/Conference (poster)

MaestroMotif: Skill Design from Artificial Intelligence Feedback

Martin Klissarov

Mikael Henaff

Roberta Raileanu

Shagun Sodhani

Amy Zhang

Marlos C. Machado

Describing skills in natural language has the potential to provide an accessible way to inject human knowledge about decision-making into an… (see more) AI system. We present MaestroMotif, a method for AI-assisted skill design, which yields high-performing and adaptable agents. MaestroMotif leverages the capabilities of Large Language Models (LLMs) to effectively create and reuse skills. It first uses an LLM's feedback to automatically design rewards corresponding to each skill, starting from their natural language description. Then, it employs an LLM's code generation abilities, together with reinforcement learning, for training the skills and combining them to implement complex behaviors specified in language. We evaluate MaestroMotif using a suite of complex tasks in the NetHack Learning Environment (NLE), demonstrating that it surpasses existing approaches in both performance and usability.

2025-01-22

ICLR.cc/2025/Conference (oral)

Nazanin Mohammadi Sepahvand

Selective Unlearning via Representation Erasure Using Domain Adversarial Training

Eleni Triantafillou

Hugo Larochelle

Gintare Karolina Dziugaite

James J. Clark

Daniel M. Roy

When deploying machine learning models in the real world, we often face the challenge of “unlearning” specific data points or subsets a… (see more)fter training. Inspired by Domain-Adversarial Training of Neural Networks (DANN), we propose a novel algorithm,SURE, for targeted unlearning.SURE treats the process as a domain adaptation problem, where the “forget set” (data to be removed) and a validation set from the same distribution form two distinct domains. We train a domain classifier to discriminate between representations from the forget and validation sets.Using a gradient reversal strategy similar to DANN, we perform gradient updates to the representations to “fool” the domain classifier and thus obfuscate representations belonging to the forget set. Simultaneously, gradient descent is applied to the retain set (original training data minus the forget set) to preserve its classification performance. Unlike other unlearning approaches whose training objectives are built based on model outputs, SURE directly manipulates the representations.This is key to ensure robustness against a set of more powerful attacks than currently considered in the literature, that aim to detect which examples were unlearned through access to learned embeddings. Our thorough experiments reveal that SURE has a better unlearning quality to utility trade-off compared to other standard unlearning techniques for deep neural networks.

2025-01-22

ICLR.cc/2025/Conference (poster)

Nazanin Mohammadi Sepahvand

Selective Unlearning via Representation Erasure Using Domain Adversarial Training

Eleni Triantafillou

Hugo Larochelle

Gintare Karolina Dziugaite

James J. Clark

Daniel M. Roy

2025-01-22

ICLR.cc/2025/Conference (poster)

Training Language Models to Self-Correct via Reinforcement Learning

Aviral Kumar

Vincent Zhuang

Rishabh Agarwal

Yi Su

John D Co-Reyes

Avi Singh

Kate Baumli

Shariq Iqbal

Colton Bishop

Rebecca Roelofs

Lei M Zhang

Kay McKinney

Disha Shrivastava

Cosmin Paduraru

George Tucker

Feryal Behbahani

Aleksandra Faust

Self-correction is a highly desirable capability of large language models (LLMs), yet it has consistently been found to be largely ineffecti… (see more)ve in modern LLMs. Existing approaches for training self-correction either require multiple models or rely on a more capable model or other forms of supervision. To this end, we develop a multi-turn online reinforcement learning (RL) approach, SCoRe, that significantly improves an LLM's self-correction ability using entirely self-generated data. To build SCoRe, we first show that variants of supervised fine-tuning (SFT) on offline model-generated correction traces are insufficient for instilling self-correction behavior. In particular, we observe that training via SFT either suffers from a distribution mismatch between the training data and the model's own responses or implicitly prefers only a certain mode of correction behavior that is often not effective at test time. SCoRe addresses these challenges by training under the model's own distribution of self-generated correction traces and using appropriate regularization to steer the learning process into learning a self-correction strategy that is effective at test time as opposed to simply fitting high-reward responses for a given prompt. This regularization prescribes running a first phase of RL on a base model to generate a policy initialization that is less susceptible to collapse and then using a reward bonus to amplify self-correction during training. When applied to Gemini 1.0 Pro and 1.5 Flash models, we find that SCoRe achieves state-of-the-art self-correction performance, improving the base models' self-correction by 15.6% and 9.1% respectively on the MATH and HumanEval benchmarks.

2025-01-01

ICLR (published)

Fairness in Reinforcement Learning with Bisimulation Metrics

Sahand Rezaei-Shoshtari

Hanna Yurchyk

Scott Fujimoto

David Meger

Ensuring long-term fairness is crucial when developing automated decision making systems, specifically in dynamic and sequential environment… (see more)s. By maximizing their reward without consideration of fairness, AI agents can introduce disparities in their treatment of groups or individuals. In this paper, we establish the connection between bisimulation metrics and group fairness in reinforcement learning. We propose a novel approach that leverages bisimulation metrics to learn reward functions and observation dynamics, ensuring that learners treat groups fairly while reflecting the original problem. We demonstrate the effectiveness of our method in addressing disparities in sequential decision making problems through empirical evaluation on a standard fairness benchmark consisting of lending and college admission scenarios.

2024-12-22

ArXiv (preprint)

Fairness in Reinforcement Learning with Bisimulation Metrics

Sahand Rezaei-Shoshtari

Hanna Yurchyk

Scott Fujimoto

David Meger

2024-12-22

ArXiv (preprint)

MaestroMotif: Skill Design from Artificial Intelligence Feedback

Martin Klissarov

Mikael Henaff

Roberta Raileanu

Shagun Sodhani

Amy Zhang

Marlos C. Machado

2024-12-11

ArXiv (preprint)

MaestroMotif: Skill Design from Artificial Intelligence Feedback

Martin Klissarov

Mikael Henaff

Roberta Raileanu

Shagun Sodhani

Amy Zhang

Marlos C. Machado

2024-12-11

ArXiv (preprint)

Towards AI-designed genomes using a variational autoencoder

Natasha K. Dudek

N.K. Dudek

Synthetic biology holds great promise for bioengineering applications such as environmental bioremediation, probiotic formulation, and produ… (see more)ction of renewable biofuels. Humans’ capacity to design biological systems from scratch is limited by their sheer size and complexity. We introduce a framework for training a machine learning model to learn the basic genetic principles underlying the gene composition of bacterial genomes. Our variational autoencoder model, DeepGenomeVector, was trained to take as input corrupted bacterial genetic blueprints (i.e. complete gene sets, henceforth ‘genome vectors’) in which most genes had been “removed”, and re-create the original. The resulting model effectively captures the complex dependencies in genomic networks, as evaluated by both qualitative and quantitative metrics. An in-depth functional analysis of a generated gene vector shows that its encoded pathways are interconnected and nearly complete. On the test set, where the model’s ability to re-generate the original, uncorrupted genome vector was evaluated, an AUC score of 0.98 and an F1 score of 0.82 provide support for the model’s ability to generate diverse, high-quality genome vectors. This work showcases the power of machine learning approaches for synthetic biology and highlights the possibility that just as humans can design an AI that animates a robot, AIs may one day be able to design a genomic blueprint that animates a carbon-based cell. SIGNIFICANCE STATEMENT Genomes serve as the blueprints for life, encoding complex networks of genes whose products must seamlessly interact to result in living organisms. In this work, we develop a framework for training a machine learning algorithm to learn the basic genetic principles that underlie genome composition. This innovation may eventually lead to improvements in the genome design process, increasing the speed and reliability of designs while decreasing cost. It further suggests that AI agents may one day have the potential to design blueprints for carbon-based life.

2024-12-11

Proceedings of the Royal Society B: Biological Sciences (published)