Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Pierre-Luc Bacon

An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning


Mar 10, 2021
Dilip Arumugam, Peter Henderson, Pierre-Luc Bacon

* Workshop on Biological and Artificial Reinforcement Learning (NeurIPS 2020) 

  Access Paper or Ask Questions

XLVIN: eXecuted Latent Value Iteration Nets


Oct 25, 2020
Andreea Deac, Petar Veličković, Ognjen Milinković, Pierre-Luc Bacon, Jian Tang, Mladen Nikolić

* NeurIPS 2020 Deep Reinforcement Learning Workshop 

  Access Paper or Ask Questions

Graph neural induction of value iteration


Sep 26, 2020
Andreea Deac, Pierre-Luc Bacon, Jian Tang

* ICML GRL+ 2020 

  Access Paper or Ask Questions

TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning?


Jul 06, 2020
Joshua Romoff, Peter Henderson, David Kanaa, Emmanuel Bengio, Ahmed Touati, Pierre-Luc Bacon, Joelle Pineau

* Presented at the Theoretical Foundations of Reinforcement Learning workshop at ICML 2020 

  Access Paper or Ask Questions

Policy Evaluation Networks


Feb 26, 2020
Jean Harb, Tom Schaul, Doina Precup, Pierre-Luc Bacon

* 12 pages, 11 figures 

  Access Paper or Ask Questions

Options of Interest: Temporal Abstraction with Interest Functions


Jan 01, 2020
Khimya Khetarpal, Martin Klissarov, Maxime Chevalier-Boisvert, Pierre-Luc Bacon, Doina Precup

* To appear in Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20) 

  Access Paper or Ask Questions

Entropy Regularization with Discounted Future State Distribution in Policy Gradient Methods


Dec 11, 2019
Riashat Islam, Raihan Seraj, Pierre-Luc Bacon, Doina Precup

* In Submission; Appeared at NeurIPS 2019 Optimization Foundations of Reinforcement Learning Workshop 

  Access Paper or Ask Questions

All-Action Policy Gradient Methods: A Numerical Integration Approach


Oct 21, 2019
Benjamin Petit, Loren Amdahl-Culleton, Yao Liu, Jimmy Smith, Pierre-Luc Bacon

* 9 pages, 2 figures. NeurIPS 2019 Optimization Foundations of Reinforcement Learning Workshop 

  Access Paper or Ask Questions

Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling


Oct 15, 2019
Yao Liu, Pierre-Luc Bacon, Emma Brunskill

* 21 pages, 1 figure, in submission 

  Access Paper or Ask Questions

The Barbados 2018 List of Open Issues in Continual Learning


Nov 16, 2018
Tom Schaul, Hado van Hasselt, Joseph Modayil, Martha White, Adam White, Pierre-Luc Bacon, Jean Harb, Shibl Mourad, Marc Bellemare, Doina Precup

* NIPS Continual Learning Workshop 2018 

  Access Paper or Ask Questions

Convergent Tree Backup and Retrace with Function Approximation


Oct 22, 2018
Ahmed Touati, Pierre-Luc Bacon, Doina Precup, Pascal Vincent


  Access Paper or Ask Questions

Learning Robust Options


Feb 09, 2018
Daniel J. Mankowitz, Timothy A. Mann, Pierre-Luc Bacon, Doina Precup, Shie Mannor


  Access Paper or Ask Questions

Learning with Options that Terminate Off-Policy


Dec 02, 2017
Anna Harutyunyan, Peter Vrancx, Pierre-Luc Bacon, Doina Precup, Ann Nowe

* AAAI 2018 

  Access Paper or Ask Questions

Learnings Options End-to-End for Continuous Action Tasks


Nov 30, 2017
Martin Klissarov, Pierre-Luc Bacon, Jean Harb, Doina Precup


  Access Paper or Ask Questions

OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning


Nov 24, 2017
Peter Henderson, Wei-Di Chang, Pierre-Luc Bacon, David Meger, Joelle Pineau, Doina Precup

* Accepted to the Thirthy-Second AAAI Conference On Artificial Intelligence (AAAI), 2018 

  Access Paper or Ask Questions

When Waiting is not an Option : Learning Options with a Deliberation Cost


Sep 14, 2017
Jean Harb, Pierre-Luc Bacon, Martin Klissarov, Doina Precup


  Access Paper or Ask Questions

A Matrix Splitting Perspective on Planning with Options


Jul 10, 2017
Pierre-Luc Bacon, Doina Precup

* The results presented in the previous version of this paper were found be applicable only to "gating execution" and not "call-and-return". We made this distinction clear in the text and added an extension to the call-and-return model 

  Access Paper or Ask Questions

The Option-Critic Architecture


Dec 03, 2016
Pierre-Luc Bacon, Jean Harb, Doina Precup

* Accepted to the Thirthy-first AAAI Conference On Artificial Intelligence (AAAI), 2017 

  Access Paper or Ask Questions

Conditional Computation in Neural Networks for faster models


Jan 07, 2016
Emmanuel Bengio, Pierre-Luc Bacon, Joelle Pineau, Doina Precup

* ICLR 2016 submission, revised 

  Access Paper or Ask Questions