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 Philip Bachman

Philip Bachman

McGill University

Pretraining Representations for Data-Efficient Reinforcement Learning


Jun 09, 2021
Max Schwarzer, Nitarshan Rajkumar, Michael Noukhovitch, Ankesh Anand, Laurent Charlin, Devon Hjelm, Philip Bachman, Aaron Courville


  Access Paper or Ask Questions

Representation Learning with Video Deep InfoMax


Jul 28, 2020
R Devon Hjelm, Philip Bachman


  Access Paper or Ask Questions

Data-Efficient Reinforcement Learning with Momentum Predictive Representations


Jul 12, 2020
Max Schwarzer, Ankesh Anand, Rishab Goel, R Devon Hjelm, Aaron Courville, Philip Bachman

* The first two authors contributed equally to this work 

  Access Paper or Ask Questions

Deep Reinforcement and InfoMax Learning


Jun 12, 2020
Bogdan Mazoure, Remi Tachet des Combes, Thang Doan, Philip Bachman, R Devon Hjelm


  Access Paper or Ask Questions

Learning Representations by Maximizing Mutual Information Across Views


Jun 03, 2019
Philip Bachman, R Devon Hjelm, William Buchwalter


  Access Paper or Ask Questions

Learning Invariances for Policy Generalization


Sep 07, 2018
Remi Tachet des Combes, Philip Bachman, Harm van Seijen

* 7 pages, 1 figure 

  Access Paper or Ask Questions

VFunc: a Deep Generative Model for Functions


Jul 11, 2018
Philip Bachman, Riashat Islam, Alessandro Sordoni, Zafarali Ahmed

* To be presented at the ICML 2018 workshop on Prediction and Generative Modeling in Reinforcement Learning 

  Access Paper or Ask Questions

Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data


Jun 18, 2018
Amjad Almahairi, Sai Rajeswar, Alessandro Sordoni, Philip Bachman, Aaron Courville

* ICML 2018 

  Access Paper or Ask Questions

Deep Reinforcement Learning that Matters


Nov 24, 2017
Peter Henderson, Riashat Islam, Philip Bachman, Joelle Pineau, Doina Precup, David Meger

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

  Access Paper or Ask Questions

Variational Generative Stochastic Networks with Collaborative Shaping


Aug 02, 2017
Philip Bachman, Doina Precup

* Old paper, from ICML 2015 

  Access Paper or Ask Questions

Learning Algorithms for Active Learning


Jul 31, 2017
Philip Bachman, Alessandro Sordoni, Adam Trischler

* Accepted for publication at ICML 2017 

  Access Paper or Ask Questions

Machine Comprehension by Text-to-Text Neural Question Generation


May 15, 2017
Xingdi Yuan, Tong Wang, Caglar Gulcehre, Alessandro Sordoni, Philip Bachman, Sandeep Subramanian, Saizheng Zhang, Adam Trischler


  Access Paper or Ask Questions

Natural Language Generation in Dialogue using Lexicalized and Delexicalized Data


Apr 21, 2017
Shikhar Sharma, Jing He, Kaheer Suleman, Hannes Schulz, Philip Bachman


  Access Paper or Ask Questions

Calibrating Energy-based Generative Adversarial Networks


Feb 24, 2017
Zihang Dai, Amjad Almahairi, Philip Bachman, Eduard Hovy, Aaron Courville

* ICLR 2017 camera ready 

  Access Paper or Ask Questions

NewsQA: A Machine Comprehension Dataset


Feb 07, 2017
Adam Trischler, Tong Wang, Xingdi Yuan, Justin Harris, Alessandro Sordoni, Philip Bachman, Kaheer Suleman


  Access Paper or Ask Questions

Towards Information-Seeking Agents


Dec 08, 2016
Philip Bachman, Alessandro Sordoni, Adam Trischler

* Under review for ICLR 2017 

  Access Paper or Ask Questions

An Architecture for Deep, Hierarchical Generative Models


Dec 08, 2016
Philip Bachman

* Published in NIPS 2016 

  Access Paper or Ask Questions

Iterative Alternating Neural Attention for Machine Reading


Nov 09, 2016
Alessandro Sordoni, Philip Bachman, Adam Trischler, Yoshua Bengio


  Access Paper or Ask Questions

Data Generation as Sequential Decision Making


Nov 03, 2015
Philip Bachman, Doina Precup

* Accepted for publication at Advances in Neural Information Processing Systems (NIPS) 2015 

  Access Paper or Ask Questions

Testing Visual Attention in Dynamic Environments


Oct 30, 2015
Philip Bachman, David Krueger, Doina Precup


  Access Paper or Ask Questions

Learning with Pseudo-Ensembles


Dec 16, 2014
Philip Bachman, Ouais Alsharif, Doina Precup

* To appear in Advances in Neural Information Processing Systems 27 (NIPS 2014), Advances in Neural Information Processing Systems 27, Dec. 2014 

  Access Paper or Ask Questions

Representation as a Service


Jul 09, 2014
Ouais Alsharif, Philip Bachman, Joelle Pineau

* 8 pages 

  Access Paper or Ask Questions

Improved Estimation in Time Varying Models


Jun 27, 2012
Doina Precup, Philip Bachman

* Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012) 

  Access Paper or Ask Questions