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 Doina Precup

Doina Precup

McGill University, Mila- Quebec Artificial Intelligence Institute

Variance Penalized On-Policy and Off-Policy Actor-Critic


Feb 03, 2021
Arushi Jain, Gandharv Patil, Ayush Jain, Khimya Khetarpal, Doina Precup

* Accepted to the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), 2021 

  Access Paper or Ask Questions

Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards


Dec 26, 2020
Susan Amin, Maziar Gomrokchi, Hossein Aboutalebi, Harsh Satija, Doina Precup


  Access Paper or Ask Questions

Towards Continual Reinforcement Learning: A Review and Perspectives


Dec 25, 2020
Khimya Khetarpal, Matthew Riemer, Irina Rish, Doina Precup

* Preprint, 52 pages, 8 figures 

  Access Paper or Ask Questions

Gradient Starvation: A Learning Proclivity in Neural Networks


Nov 23, 2020
Mohammad Pezeshki, Sékou-Oumar Kaba, Yoshua Bengio, Aaron Courville, Doina Precup, Guillaume Lajoie


  Access Paper or Ask Questions

Diversity-Enriched Option-Critic


Nov 04, 2020
Anand Kamat, Doina Precup


  Access Paper or Ask Questions

A Study of Policy Gradient on a Class of Exactly Solvable Models


Nov 03, 2020
Gavin McCracken, Colin Daniels, Rosie Zhao, Anna Brandenberger, Prakash Panangaden, Doina Precup


  Access Paper or Ask Questions

Forethought and Hindsight in Credit Assignment


Oct 26, 2020
Veronica Chelu, Doina Precup, Hado van Hasselt


  Access Paper or Ask Questions

Connecting Weighted Automata, Tensor Networks and Recurrent Neural Networks through Spectral Learning


Oct 19, 2020
Tianyu Li, Doina Precup, Guillaume Rabusseau

* Extended version of AISTATS paper (arXiv:1807.01406) Preprint (under review). arXiv admin note: text overlap with arXiv:1807.01406 

  Access Paper or Ask Questions

A Fully Tensorized Recurrent Neural Network


Oct 13, 2020
Charles C. Onu, Jacob E. Miller, Doina Precup


  Access Paper or Ask Questions

Reward Propagation Using Graph Convolutional Networks


Oct 06, 2020
Martin Klissarov, Doina Precup


  Access Paper or Ask Questions

Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks


Sep 15, 2020
Sitao Luan, Mingde Zhao, Chenqing Hua, Xiao-Wen Chang, Doina Precup


  Access Paper or Ask Questions

Training Matters: Unlocking Potentials of Deeper Graph Convolutional Neural Networks


Aug 20, 2020
Sitao Luan, Mingde Zhao, Xiao-Wen Chang, Doina Precup


  Access Paper or Ask Questions

An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay


Jul 12, 2020
Scott Fujimoto, David Meger, Doina Precup


  Access Paper or Ask Questions

A Brief Look at Generalization in Visual Meta-Reinforcement Learning


Jul 03, 2020
Safa Alver, Doina Precup

* Accepted to the 4th Lifelong Learning Workshop at ICML 2020 

  Access Paper or Ask Questions

What can I do here? A Theory of Affordances in Reinforcement Learning


Jun 26, 2020
Khimya Khetarpal, Zafarali Ahmed, Gheorghe Comanici, David Abel, Doina Precup

* Thirty-seventh International Conference on Machine Learning (ICML 2020) 

  Access Paper or Ask Questions

Learning to Prove from Synthetic Theorems


Jun 19, 2020
Eser Aygün, Zafarali Ahmed, Ankit Anand, Vlad Firoiu, Xavier Glorot, Laurent Orseau, Doina Precup, Shibl Mourad

* 17 pages, 6 figures, submitted to NeurIPS 2020 

  Access Paper or Ask Questions

Learning to cooperate: Emergent communication in multi-agent navigation


Apr 02, 2020
Ivana Kajić, Eser Aygün, Doina Precup


  Access Paper or Ask Questions

A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms


Mar 27, 2020
Philip Amortila, Doina Precup, Prakash Panangaden, Marc G. Bellemare

* AISTATS 2020 

  Access Paper or Ask Questions

Interference and Generalization in Temporal Difference Learning


Mar 13, 2020
Emmanuel Bengio, Joelle Pineau, Doina Precup

* Submitted to ICML 2020. 20 pages, 14 figures 

  Access Paper or Ask Questions

Invariant Causal Prediction for Block MDPs


Mar 12, 2020
Amy Zhang, Clare Lyle, Shagun Sodhani, Angelos Filos, Marta Kwiatkowska, Joelle Pineau, Yarin Gal, Doina Precup

* 16 pages, 8 figures 

  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

oIRL: Robust Adversarial Inverse Reinforcement Learning with Temporally Extended Actions


Feb 20, 2020
David Venuto, Jhelum Chakravorty, Leonard Boussioux, Junhao Wang, Gavin McCracken, Doina Precup


  Access Paper or Ask Questions

Value-driven Hindsight Modelling


Feb 19, 2020
Arthur Guez, Fabio Viola, Théophane Weber, Lars Buesing, Steven Kapturowski, Doina Precup, David Silver, Nicolas Heess

* 8 pages + reference + appendix 

  Access Paper or Ask Questions

Provably efficient reconstruction of policy networks


Feb 07, 2020
Bogdan Mazoure, Thang Doan, Tianyu Li, Vladimir Makarenkov, Joelle Pineau, Doina Precup, Guillaume Rabusseau


  Access Paper or Ask Questions

Option-critic in cooperative multi-agent systems


Jan 06, 2020
Jhelum Chakravorty, Nadeem Ward, Julien Roy, Maxime Chevalier-Boisvert, Sumana Basu, Andrei Lupu, Doina Precup


  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

Shaping representations through communication: community size effect in artificial learning systems


Dec 12, 2019
Olivier Tieleman, Angeliki Lazaridou, Shibl Mourad, Charles Blundell, Doina Precup

* NeurIPS 2019 workshop on visually grounded interaction and language 

  Access Paper or Ask Questions