Doina Precup

Samin Yeasar Arnob

PhD - McGill University

Sumana Basu

Collaborating Alumni - McGill University

Co-supervisor :

Adriana Romero Soriano

Collaborating Alumni - McGill University

Raymond Chua

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

Co-supervisor :

Isabeau Prémont-Schwarz

Franco Del Balso

Collaborating researcher - Université de Montréal

Jesse Farebrother

PhD - McGill University

Principal supervisor :

Marc Gendron-Bellemare

PhD - McGill University

Principal supervisor :

Collaborating researcher - Birla Institute of Technology

Jonathan Hu

Master's Research - McGill University

Howard Huang

PhD - McGill University

Haque Ishfaq

Collaborating Alumni - McGill University

Mohammad Sami Nur Islam Islam

Master's Research - McGill University

Hangzhan Jin

PhD - Polytechnique Montréal

Martin Klissarov

PhD - McGill University

Postdoctorate - McGill University

Jonathan Lebensold

Collaborating Alumni - McGill University

Collaborating Alumni - McGill University

Ray Luo

PhD - McGill University

Principal supervisor :

G McCracken

PhD - McGill University

Nazanin Mohammadi Sepahvand

Collaborating Alumni - 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 :

PhD - McGill University

Co-supervisor :

Research Intern - McGill University

Nate Rahn

PhD - McGill University

Principal supervisor :

Marc Gendron-Bellemare

Manoosh Samiei

PhD - McGill University

Co-supervisor :

PhD - McGill University

Co-supervisor :

PhD - McGill University

Nishanth Anand Vemgal

PhD - McGill University

PhD - McGill University

Co-supervisor :

Samira Ebrahimi Kahou

Research Intern - McGill University

Zihan Wang

PhD - McGill University

Skipper: Combining Spatial and Temporal Abstraction for Better Generalization

Steve Wen

Master's Research - McGill University

Co-supervisor :

Gregory Dudek

Zijing Wu

PhD - McGill University

Principal supervisor :

PhD - McGill University

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

What is Going on Inside Recurrent Meta Reinforcement Learning Agents?

Safa Alver

Recurrent meta reinforcement learning (meta-RL) agents are agents that employ a recurrent neural network (RNN) for the purpose of"learning a… (see more) learning algorithm". After being trained on a pre-specified task distribution, the learned weights of the agent's RNN are said to implement an efficient learning algorithm through their activity dynamics, which allows the agent to quickly solve new tasks sampled from the same distribution. However, due to the black-box nature of these agents, the way in which they work is not yet fully understood. In this study, we shed light on the internal working mechanisms of these agents by reformulating the meta-RL problem using the Partially Observable Markov Decision Process (POMDP) framework. We hypothesize that the learned activity dynamics is acting as belief states for such agents. Several illustrative experiments suggest that this hypothesis is true, and that recurrent meta-RL agents can be viewed as agents that learn to act optimally in partially observable environments consisting of multiple related tasks. This view helps in understanding their failure cases and some interesting model-based results reported in the literature.

2021-04-28

ArXiv (preprint)

Safe Option-Critic: Learning Safety in the Option-Critic Architecture

Arushi Jain

Khimya Khetarpal

Designing hierarchical reinforcement learning algorithms that exhibit safe behaviour is not only vital for practical applications but also, … (see more)facilitates a better understanding of an agent's decisions. We tackle this problem in the options framework, a particular way to specify temporally abstract actions which allow an agent to use sub-policies with start and end conditions. We consider a behaviour as safe that avoids regions of state-space with high uncertainty in the outcomes of actions. We propose an optimization objective that learns safe options by encouraging the agent to visit states with higher behavioural consistency. The proposed objective results in a trade-off between maximizing the standard expected return and minimizing the effect of model uncertainty in the return. We propose a policy gradient algorithm to optimize the constrained objective function. We examine the quantitative and qualitative behaviour of the proposed approach in a tabular grid-world, continuous-state puddle-world, and three games from the Arcade Learning Environment: Ms.Pacman, Amidar, and Q*Bert. Our approach achieves a reduction in the variance of return, boosts performance in environments with intrinsic variability in the reward structure, and compares favorably both with primitive actions as well as with risk-neutral options.

2021-04-06

The Knowledge Engineering Review (published)

Training a First-Order Theorem Prover from Synthetic Data

Vlad Firoiu

Eser Aygün

Ankit Anand

Zafarali Ahmed

Xavier Glorot

Laurent Orseau

Lei Zhang

Shibl Mourad

2021-03-04

ArXiv (preprint)

A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning

Mingde Zhao

We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state during plan… (see more)ning. The agent uses a bottleneck mechanism over a set-based representation to force the number of entities to which the agent attends at each planning step to be small. In experiments, we investigate the bottleneck mechanism with several sets of customized environments featuring different challenges. We consistently observe that the design allows the planning agents to generalize their learned task-solving abilities in compatible unseen environments by attending to the relevant objects, leading to better out-of-distribution generalization performance.

2020-12-31

Neural Information Processing Systems (published)

Correcting Momentum in Temporal Difference Learning

Emmanuel Bengio

Joelle Pineau

A common optimization tool used in deep reinforcement learning is momentum, which consists in accumulating and discounting past gradients, r… (see more)eapplying them at each iteration. We argue that, unlike in supervised learning, momentum in Temporal Difference (TD) learning accumulates gradients that become doubly stale: not only does the gradient of the loss change due to parameter updates, the loss itself changes due to bootstrapping. We first show that this phenomenon exists, and then propose a first-order correction term to momentum. We show that this correction term improves sample efficiency in policy evaluation by correcting target value drift. An important insight of this work is that deep RL methods are not always best served by directly importing techniques from the supervised setting.

2020-12-31

arXiv (preprint)

Finite time analysis of temporal difference learning with linear function approximation: the tail averaged case

Gandharv Patil

Prashanth L.A.

In this paper, we study the ﬁnite-time behaviour of temporal difference (TD) learning algorithms when combined with tail-averaging, and pr… (see more)esent instance dependent bounds on the parameter error of the tail-averaged TD iterate. Our error bounds hold in expectation as well as with high probability, exhibit a sharper rate of decay for the initial error (bias), and are comparable with existing bounds in the literature.

2020-12-31

(published)

www.semanticscholar.org

Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation

This paper is about the problem of learning a stochastic policy for generating an object (like a molecular graph) from a sequence of actions… (see more), such that the probability of generating an object is proportional to a given positive reward for that object. Whereas standard return maximization tends to converge to a single return-maximizing sequence, there are cases where we would like to sample a diverse set of high-return solutions. These arise, for example, in black-box function optimization when few rounds are possible, each with large batches of queries, where the batches should be diverse, e.g., in the design of new molecules. One can also see this as a problem of approximately converting an energy function to a generative distribution. While MCMC methods can achieve that, they are expensive and generally only perform local exploration. Instead, training a generative policy amortizes the cost of search during training and yields to fast generation. Using insights from Temporal Difference learning, we propose GFlowNet, based on a view of the generative process as a flow network, making it possible to handle the tricky case where different trajectories can yield the same final state, e.g., there are many ways to sequentially add atoms to generate some molecular graph. We cast the set of trajectories as a flow and convert the flow consistency equations into a learning objective, akin to the casting of the Bellman equations into Temporal Difference methods. We prove that any global minimum of the proposed objectives yields a policy which samples from the desired distribution, and demonstrate the improved performance and diversity of GFlowNet on a simple domain where there are many modes to the reward function, and on a molecule synthesis task.

2020-12-31

NeurIPS (published)

Improving Long-Term Metrics in Recommendation Systems using Short-Horizon Offline RL

Bogdan Mazoure

Paul Mineiro

Pavithra Srinath

Reza Sharifi Sedeh

Adith Swaminathan

We study session-based recommendation scenarios where we want to recommend items to users during sequential interactions to improve their lo… (see more)ng-term utility. Optimizing a long-term metric is challenging because the learning signal (whether the recommendations achieved their desired goals) is delayed and confounded by other user interactions with the system. Immediately measurable proxies such as clicks can lead to suboptimal recommendations due to misalignment with the long-term metric. Many works have applied episodic reinforcement learning (RL) techniques for session-based recommendation but these methods do not account for policy-induced drift in user intent across sessions. We develop a new batch RL algorithm called Short Horizon Policy Improvement (SHPI) that approximates policy-induced distribution shifts across sessions. By varying the horizon hyper-parameter in SHPI, we recover well-known policy improvement schemes in the RL literature. Empirical results on four recommendation tasks show that SHPI can outperform matrix factorization, offline bandits, and offline RL baselines. We also provide a stable and computationally efficient implementation using weighted regression oracles.

2020-12-31

arXiv.org (preprint)

dblp.uni-trier.de

Optimal Spectral-Norm Approximate Minimization of Weighted Finite Automata

Borja Balle

We address the approximate minimization problem for weighted finite automata (WFAs) with weights in …

2020-12-31

arXiv (preprint)

Preferential Temporal Difference Learning

Nishanth Anand

Temporal-Difference (TD) learning is a general and very useful tool for estimating the value function of a given policy, which in turn is re… (see more)quired to find good policies. Generally speaking, TD learning updates states whenever they are visited. When the agent lands in a state, its value can be used to compute the TD-error, which is then propagated to other states. However, it may be interesting, when computing updates, to take into account other information than whether a state is visited or not. For example, some states might be more important than others (such as states which are frequently seen in a successful trajectory). Or, some states might have unreliable value estimates (for example, due to partial observability or lack of data), making their values less desirable as targets. We propose an approach to re-weighting states used in TD updates, both when they are the input and when they provide the target for the update. We prove that our approach converges with linear function approximation and illustrate its desirable empirical behaviour compared to other TD-style methods.

2020-12-31

ICML (published)

proceedings.mlr.press

Randomized Least Squares Policy Optimization

Haque Ishfaq

Zhuoran Yang

Andrei Lupu

Viet Bang Nguyen

Lewis Liu

Riashat Islam

Zhaoran Wang

Policy Optimization (PO) methods with function approximation are one of the most popular classes of Reinforcement Learning (RL) algorithms. … (see more)However, designing provably efﬁcient policy optimization algorithms remains a challenge. Recent work in this area has focused on incorporating upper conﬁdence bound (UCB)-style bonuses to drive exploration in policy optimization. In this paper, we present Randomized Least Squares Policy Optimization (RLSPO) which is inspired by Thompson Sampling. We prove that, in an episodic linear kernel MDP setting, RLSPO achieves (cid:101) O ( d 3 / 2 H 3 / 2 √ T ) worst-case (frequentist) regret, where H is the number of episodes, T is the total number of steps and d is the feature dimension. Finally, we evaluate RLSPO empirically and show that it is competitive with existing provably efﬁcient PO algorithms.

2020-12-31

(published)

www.semanticscholar.org

Temporally Abstract Partial Models

Khimya Khetarpal

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 demonstrate empirically the potential impact of partial option models on the efficiency of planning.

2020-12-31

Advances in Neural Information Processing Systems 34 (NeurIPS 2021) (published)