David Meger

Valliappan Chidambaram Adaikkappan

PhD - McGill University

Google Scholar

Wesley Chung

PhD - McGill University

Co-supervisor :

Doina Precup

Farnoosh Faraji

PhD - McGill University

Co-supervisor :

Master's Research - McGill University

Co-supervisor :

Hsiu-Chin Lin

Zina Kamel

Master's Research - McGill University

Co-supervisor :

Hsiu-Chin Lin

Sahand Rezaei-Shoshtari

PhD - McGill University

Principal supervisor :

PhD - McGill University

Junming(Clark) Shi

Master's Research - McGill University

Steven Wang

Master's Research - McGill University

Harley Wiltzer

PhD - McGill University

Co-supervisor :

Marc Gendron-Bellemare

PhD - McGill University

Publications

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

Scott Fujimoto

Wei-Di Chang

Edward J. Smith

Shixiang Shane Gu

Doina Precup

In the field of reinforcement learning (RL), representation learning is a proven tool for complex image-based tasks, but is often overlooked… (see more) 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.

2023-09-20

NeurIPS.cc/2023/Conference (poster)

Leveraging World Model Disentanglement in Value-Based Multi-Agent Reinforcement Learning

Zhizun Wang

In this paper, we propose a novel model-based multi-agent reinforcement learning approach named Value Decomposition Framework with Disentang… (see more)led World Model to address the challenge of achieving a common goal of multiple agents interacting in the same environment with reduced sample complexity. Due to scalability and non-stationarity problems posed by multi-agent systems, model-free methods rely on a considerable number of samples for training. In contrast, we use a modularized world model, composed of action-conditioned, action-free, and static branches, to unravel the environment dynamics and produce imagined outcomes based on past experience, without sampling directly from the real environment. We employ variational auto-encoders and variational graph auto-encoders to learn the latent representations for the world model, which is merged with a value-based framework to predict the joint action-value function and optimize the overall training objective. We present experimental results in Easy, Hard, and Super-Hard StarCraft II micro-management challenges to demonstrate that our method achieves high sample efficiency and exhibits superior performance in defeating the enemy armies compared to other baselines.

2023-09-07

ArXiv (preprint)

Efficient Epistemic Uncertainty Estimation in Regression Ensemble Models Using Pairwise-Distance Estimators

Lucas Berry

This work introduces an efficient novel approach for epistemic uncertainty estimation for ensemble models for regression tasks using pairwis… (see more)e-distance estimators (PaiDEs). Utilizing the pairwise-distance between model components, these estimators establish bounds on entropy. We leverage this capability to enhance the performance of Bayesian Active Learning by Disagreement (BALD). Notably, unlike sample-based Monte Carlo estimators, PaiDEs exhibit a remarkable capability to estimate epistemic uncertainty at speeds up to 100 times faster while covering a significantly larger number of inputs at once and demonstrating superior performance in higher dimensions. To validate our approach, we conducted a varied series of regression experiments on commonly used benchmarks: 1D sinusoidal data,

2023-08-24

ArXiv (preprint)

Hypernetworks for Zero-shot Transfer in Reinforcement Learning

Sahand Rezaei-Shoshtari

Charlotte Morissette

Francois R. Hogan

Gregory Dudek

In this paper, hypernetworks are trained to generate behaviors across a range of unseen task conditions, via a novel TD-based training objec… (see more)tive and data from a set of near-optimal RL solutions for training tasks. This work relates to meta RL, contextual RL, and transfer learning, with a particular focus on zero-shot performance at test time, enabled by knowledge of the task parameters (also known as context). Our technical approach is based upon viewing each RL algorithm as a mapping from the MDP specifics to the near-optimal value function and policy and seek to approximate it with a hypernetwork that can generate near-optimal value functions and policies, given the parameters of the MDP. We show that, under certain conditions, this mapping can be considered as a supervised learning problem. We empirically evaluate the effectiveness of our method for zero-shot transfer to new reward and transition dynamics on a series of continuous control tasks from DeepMind Control Suite. Our method demonstrates significant improvements over baselines from multitask and meta RL approaches.

2023-06-25

Proceedings of the AAAI Conference on Artificial Intelligence (published)

ANSEL Photobot: A Robot Event Photographer with Semantic Intelligence

Dmitriy Rivkin

Gregory Dudek

Nikhil Kakodkar

Oliver Limoyo

Xue Liu

Francois Hogan

Our work examines the way in which large language models can be used for robotic planning and sampling, specifically the context of automate… (see more)d photographic documentation. Specifically, we illustrate how to produce a photo-taking robot with an exceptional level of semantic awareness by leveraging recent advances in general purpose language (LM) and vision-language (VLM) models. Given a high-level description of an event we use an LM to generate a natural-language list of photo descriptions that one would expect a photographer to capture at the event. We then use a VLM to identify the best matches to these descriptions in the robot's video stream. The photo portfolios generated by our method are consistently rated as more appropriate to the event by human evaluators than those generated by existing methods.

2023-06-01

2023 IEEE International Conference on Robotics and Automation (ICRA) (published)

Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modeling

Lucas Berry

2023-02-01

ArXiv (preprint)

Bayesian Q-learning With Imperfect Expert Demonstrations

Xiru Zhu

Guided exploration with expert demonstrations improves data efficiency for reinforcement learning, but current algorithms often overuse expe… (see more)rt information. We propose a novel algorithm to speed up Q-learning with the help of a limited amount of imperfect expert demonstrations. The algorithm avoids excessive reliance on expert data by relaxing the optimal expert assumption and gradually reducing the usage of uninformative expert data. Experimentally, we evaluate our approach on a sparse-reward chain environment and six more complicated Atari games with delayed rewards. With the proposed methods, we can achieve better results than Deep Q-learning from Demonstrations (Hester et al., 2017) in most environments.

2022-12-08

NeurIPS.cc/2022/Workshop/DeepRL (accepted)

Learning Successor Feature Representations to Train Robust Policies for Multi-task Learning

Melissa Mozifian

Dieter Fox

Fabio Ramos

Animesh Garg

The deep reinforcement learning (RL) framework has shown great promise to tackle sequential decision-making problems, where the agent learns… (see more) to behave optimally through interactions with the environment and receiving rewards. The ability of an RL agent to learn different reward functions concurrently has many benefits, such as the decomposition of task rewards and promoting skill reuse. In this paper, we consider the problem of continuous control for robot manipulation tasks with an explicit representation that promotes skill reuse while learning multiple tasks with similar reward functions. Our approach relies on two key concepts: successor features (SFs), a value function representation that decouples the dynamics of the environment from the rewards, and an actor-critic framework that incorporates the learned SFs representation. SFs form a natural bridge between model-based and model-free RL methods. We first show how to learn a decomposable representation required by SFs as a pre-training stage. The proposed architecture is able to learn decoupled state and reward feature representations for non-linear reward functions. We then evaluate the feasibility of integrating SFs into an actor-critic framework, which is more tailored for tasks solved with deep RL algorithms. The approach is empirically tested on non-trivial continuous control problems with compositional structure built into the reward functions of the tasks.

2022-12-08

NeurIPS.cc/2022/Workshop/DeepRL (unknown)

NeurIPS 2022 Competition: Driving SMARTS

Amir Hossein Rasouli

R. Goebel

Matthew E. Taylor

Iuliia Kotseruba

Soheil Alizadeh

Tianpei Yang

Montgomery Alban

Florian Shkurti

Yuzheng Zhuang

Adam Ścibior

Kasra Rezaee

Animesh Garg

Jun Luo

Liam Paull

Weinan Zhang

Xinyu Wang

Xiangshan Chen

2022-11-13

ArXiv (preprint)

Uncertainty-Driven Active Vision for Implicit Scene Reconstruction

Edward J. Smith

Michal Drozdzal

D. Nowrouzezahrai

Adriana Romero

2022-10-02

ArXiv (preprint)

Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning

Harley Wiltzer

Bellemare Marc-Emmanuel

Continuous-time reinforcement learning offers an appealing formalism for describing control problems in which the passage of time is not nat… (see more)urally divided into discrete increments. Here we consider the problem of predicting the distribution of returns obtained by an agent interacting in a continuous-time, stochastic environment. Accurate return predictions have proven useful for determining optimal policies for risk-sensitive control, learning state representations, multiagent coordination, and more. We begin by establishing the distributional analogue of the Hamilton-Jacobi-Bellman (HJB) equation for Itô diffusions and the broader class of Feller-Dynkin processes. We then specialize this equation to the setting in which the return distribution is approximated by

2022-06-27

Proceedings of the 39th International Conference on Machine Learning (published)

proceedings.mlr.press

Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error

Scott Fujimoto

Doina Precup

Ofir Nachum

Shixiang Shane Gu

In this work, we study the use of the Bellman equation as a surrogate objective for value prediction accuracy. While the Bellman equation is… (see more) uniquely solved by the true value function over all state-action pairs, we find that the Bellman error (the difference between both sides of the equation) is a poor proxy for the accuracy of the value function. In particular, we show that (1) due to cancellations from both sides of the Bellman equation, the magnitude of the Bellman error is only weakly related to the distance to the true value function, even when considering all state-action pairs, and (2) in the finite data regime, the Bellman equation can be satisfied exactly by infinitely many suboptimal solutions. This means that the Bellman error can be minimized without improving the accuracy of the value function. We demonstrate these phenomena through a series of propositions, illustrative toy examples, and empirical analysis in standard benchmark domains.

2022-06-27

Proceedings of the 39th International Conference on Machine Learning (published)