Marc G. Bellemare

Core Industry Member
Marc G. Bellemare
Adjunct Professor, Assistant Professor, McGill University, Google
Marc G. Bellemare

I am a research scientist at Google Brain in Montréal, Canada focusing on the reinforcement learning effort there. From 2013 to 2017 I was at DeepMind in the UK. I received my Ph.D. from the University of Alberta working with Michael Bowling and Joel Veness.

My research lies at the intersection of reinforcement learning and probabilistic prediction. I’m also interested in deep learning, generative modelling, online learning, and information theory.

Publications

2020-09

The Importance of Pessimism in Fixed-Dataset Policy Optimization
Jacob Buckman, Carles Gelada and Marc G. Bellemare
arXiv preprint arXiv:2009.06799
(2020-09-15)
arxiv.orgPDF

2020-07

Representations for Stable Off-Policy Reinforcement Learning
Dibya Ghosh and Marc Bellemare

2020-06

The Value-Improvement Path: Towards Better Representations for Reinforcement Learning
Will Dabney, André Barreto, Mark Rowland, Robert Dadashi, John Quan, Marc G. Bellemare and David Silver
arXiv preprint arXiv:2006.02243
(2020-06-03)
dblp.uni-trier.dePDF

2020-04

On Bonus Based Exploration Methods In The Arcade Learning Environment
Adrien Ali Taiga, William Fedus, Marlos C. Machado, Aaron Courville and Marc G. Bellemare
ICLR 2020
(2020-04-30)
iclr.ccPDF

2020-03

Zooming for Efficient Model-Free Reinforcement Learning in Metric Spaces
Ahmed Touati, Adrien Ali Taiga and Marc G. Bellemare
arXiv preprint arXiv:2003.04069
(2020-03-09)
ui.adsabs.harvard.eduPDF
The Hanabi Challenge: A New Frontier for AI Research
Nolan Bard, Jakob N. Foerster, Sarath Chandar, Neil Burch, Marc Lanctot, H. Francis Song, Emilio Parisotto, Vincent Dumoulin, Subhodeep Moitra, Edward Hughes, Iain Dunning, Shibl Mourad, Hugo Larochelle, Marc G. Bellemare and Michael Bowling
Artificial Intelligence
(2020-03-01)
www.sciencedirect.comPDF

2020-02

On Catastrophic Interference in Atari 2600 Games
William Fedus, Dibya Ghosh, John D. Martin, Marc G. Bellemare, Yoshua Bengio and Hugo Larochelle
arXiv preprint arXiv:2002.12499
(2020-02-28)
ui.adsabs.harvard.eduPDF
Count-Based Exploration with the Successor Representation
Marlos C. Machado, Marc G. Bellemare and Michael Bowling
AAAI 2020
(2020-02-07)
aaai.orgPDF
Algorithmic Improvements for Deep Reinforcement Learning applied to Interactive Fiction
Vishal Jain, Liam Fedus, Hugo Larochelle, Doina Precup and Marc G. Bellemare
AAAI 2020
(2020-02-07)
aaai.orgPDF

2020-01

Shaping the Narrative Arc: Information-Theoretic Collaborative Dialogue
Kory Mathewson, Pablo Samuel Castro, Colin Cherry, George Foster and Marc G. Bellemare
(venue unknown)
(2020-01-01)
A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms.

2019-12

A Geometric Perspective on Optimal Representations for Reinforcement Learning
Marc Bellemare, Will Dabney, Robert Dadashi-Tazehozi, Adrien Ali Taiga, Pablo Samuel Castro, Nicolas Le Roux, Dale Schuurmans, Tor Lattimore and Clare Lyle
NEURIPS 2019
(2019-12-08)
papers.nips.ccPDF

2019-11

Algorithmic Improvements for Deep Reinforcement Learning applied to Interactive Fiction
Vishal Jain, William Fedus, Hugo Larochelle, Doina Precup and Marc G. Bellemare
arXiv preprint arXiv:1911.12511
(2019-11-28)
arxiv.orgPDF

2019-08

Benchmarking Bonus-Based Exploration Methods on the Arcade Learning Environment
Adrien Ali Taïga, William Fedus, Marlos C. Machado, Aaron C. Courville and Marc G. Bellemare
arXiv preprint arXiv:1908.02388
(2019-08-06)
ui.adsabs.harvard.eduPDF
An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents.
Felipe Petroski Such, Vashisht Madhavan, Rosanne Liu, Rui Wang, Pablo Samuel Castro, Yulun Li, Jiale Zhi, Ludwig Schubert, Marc G. Bellemare, Jeff Clune and Joel Lehman

2019-06

The Value Function Polytope in Reinforcement Learning
Robert Dadashi, Marc Bellemare, Adrien Ali Taiga, Nicolas Le Roux and Dale Schuurmans
ICML 2019
(2019-06-09)
proceedings.mlr.pressPDF
Statistics and Samples in Distributional Reinforcement Learning
Mark Rowland, Robert Dadashi, Saurabh Kumar, Remi Munos, Marc Bellemare and Will Dabney
DeepMDP: Learning Continuous Latent Space Models with Theoretical Guarantees
Carles Gelada, Saurabh Kumar, Jacob Buckman, Ofir Nachum and Marc Bellemare
ICML 2019
(2019-06-09)
icml.cc

2019-05

DeepMDP: Learning Continuous Latent Space Models for Representation Learning
Carles Gelada, Saurabh Kumar, Jacob Buckman, Ofir Nachum and Marc G. Bellemare
Task-Agnostic Reinforcement Learning (TARL)
Danijar Hafner, Deepak Pathak, Frederik Ebert, Marc G Bellemare, Raia Hadsell, Rowan McAllister, Amy Zhang, Joelle Pineau, Ahmed Touati and Roberto Calandra
ICLR 2019
(2019-05-06)
iclr.cc

2019-04

Distributional reinforcement learning with linear function approximation
Marc G. Bellemare, Nicolas Le Roux, Pablo Samuel Castro and Subhodeep Moitra

2019-02

Hyperbolic Discounting and Learning over Multiple Horizons
William Fedus, Carles Gelada, Yoshua Bengio, Marc G. Bellemare and Hugo Larochelle
arXiv preprint arXiv:1902.06865
(2019-02-19)
ui.adsabs.harvard.eduPDF

2019-01

Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue.
Kory Wallace Mathewson, Pablo Samuel Castro, Colin Cherry, George F. Foster and Marc G. Bellemare
arXiv preprint arXiv:1901.11528
(2019-01-31)
dblp.uni-trier.dePDF
The Value Function Polytope in Reinforcement Learning
Robert Dadashi, Adrien Ali Taïga, Nicolas Le Roux, Dale Schuurmans and Marc G. Bellemare
arXiv preprint arXiv:1901.11524
(2019-01-31)
arxiv.orgPDF
A Geometric Perspective on Optimal Representations for Reinforcement Learning
Marc G. Bellemare, Will Dabney, Robert Dadashi, Adrien Ali Taiga, Pablo Samuel Castro, Nicolas Le Roux, Dale Schuurmans, Tor Lattimore and Clare Lyle
arXiv preprint arXiv:1901.11530
(2019-01-31)
export.arxiv.orgPDF
Off-Policy Deep Reinforcement Learning by Bootstrapping the Covariate Shift
Carles Gelada and Marc G. Bellemare
A Comparative Analysis of Expected and Distributional Reinforcement Learning
Clare Mb Lyle, Pablo Samuel Castro and Marc G. Bellemare
Temporally Extended Metrics for Markov Decision Processes.
AAAI 2019
(2019-01-01)
dblp.uni-trier.dePDF

2018-12

An Introduction to Deep Reinforcement Learning
Vincent François-Lavet, Peter Henderson, Riashat Islam, Marc G. Bellemare and Joelle Pineau
(venue unknown)
(2018-12-20)
nowpublishers.comPDF

2018-11

The Barbados 2018 List of Open Issues in Continual Learning.
Tom Schaul, Hado van Hasselt, Joseph Modayil, Martha White, Adam White, Pierre-Luc Bacon, Jean Harb, Shibl Mourad, Marc G. Bellemare and Doina Precup
arXiv preprint arXiv:1811.07004
(2018-11-16)
dblp.uni-trier.dePDF

2018-08

Approximate Exploration through State Abstraction.
Adrien Ali Taïga, Aaron C. Courville and Marc G. Bellemare
arXiv preprint arXiv:1808.09819
(2018-08-29)
dblp.uni-trier.dePDF

Publications collected and formatted using Paperoni

array(1) { ["wp-wpml_current_language"]=> string(2) "en" }