Philip Bachman

53 papers A* 14Journal 27Unranked 12

Year	Rank	Type	Title / Venue / Authors
2024	J	`jnl`	Video Occupancy Models. CoRR Manan Tomar, Philippe Hansen-Estruch, Philip Bachman, Alex Lamb, John Langford, Matthew E. Taylor, Sergey Levine
2023	A*	`conf`	Ignorance is Bliss: Robust Control via Information Gating. NeurIPS Manan Tomar, Riashat Islam, Matthew E. Taylor, Sergey Levine, Philip Bachman
2023	J	`jnl`	Ignorance is Bliss: Robust Control via Information Gating. CoRR Manan Tomar, Riashat Islam, Sergey Levine, Philip Bachman
2021	A*	`conf`	Data-Efficient Reinforcement Learning with Self-Predictive Representations. ICLR Max Schwarzer, Ankesh Anand, Rishab Goel, R. Devon Hjelm, Aaron C. Courville, Philip Bachman
2021	A*	`conf`	Decomposed Mutual Information Estimation for Contrastive Representation Learning. ICML Alessandro Sordoni, Nouha Dziri, Hannes Schulz, Geoffrey J. Gordon, Philip Bachman, Remi Tachet des Combes
2021	J	`jnl`	Decomposed Mutual Information Estimation for Contrastive Representation Learning. CoRR Alessandro Sordoni, Nouha Dziri, Hannes Schulz, Geoffrey J. Gordon, Philip Bachman, Remi Tachet des Combes
2021	A*	`conf`	Pretraining Representations for Data-Efficient Reinforcement Learning. NeurIPS Max Schwarzer, Nitarshan Rajkumar, Michael Noukhovitch, Ankesh Anand, Laurent Charlin, R. Devon Hjelm, Philip Bachman, Aaron C. Courville
2021	J	`jnl`	Pretraining Representations for Data-Efficient Reinforcement Learning. CoRR Max Schwarzer, Nitarshan Rajkumar, Michael Noukhovitch, Ankesh Anand, Laurent Charlin, R. Devon Hjelm, Philip Bachman, Aaron C. Courville
2020	J	`jnl`	Data-Efficient Reinforcement Learning with Momentum Predictive Representations. CoRR Max Schwarzer, Ankesh Anand, Rishab Goel, R. Devon Hjelm, Aaron C. Courville, Philip Bachman
2020	A*	`conf`	Deep Reinforcement and InfoMax Learning. NeurIPS Bogdan Mazoure, Remi Tachet des Combes, Thang Doan, Philip Bachman, R. Devon Hjelm
2020	J	`jnl`	Deep Reinforcement and InfoMax Learning. CoRR Bogdan Mazoure, Remi Tachet des Combes, Thang Doan, Philip Bachman, R. Devon Hjelm
2020	J	`jnl`	Representation Learning with Video Deep InfoMax. CoRR R. Devon Hjelm, Philip Bachman
2019	A*	`conf`	Learning Representations by Maximizing Mutual Information Across Views. NeurIPS Philip Bachman, R. Devon Hjelm, William Buchwalter
2019	J	`jnl`	Learning Representations by Maximizing Mutual Information Across Views. CoRR Philip Bachman, R. Devon Hjelm, William Buchwalter
2019	—	`conf`	Learning deep representations by mutual information estimation and maximization. ICLR R. Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Philip Bachman, Adam Trischler, Yoshua Bengio
2018	A*	`conf`	Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data. ICML Amjad Almahairi, Sai Rajeswar, Alessandro Sordoni, Philip Bachman, Aaron C. Courville
2018	J	`jnl`	Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data. CoRR Amjad Almahairi, Sai Rajeswar, Alessandro Sordoni, Philip Bachman, Aaron C. Courville
2018	A*	`conf`	Deep Reinforcement Learning That Matters. AAAI Peter Henderson, Riashat Islam, Philip Bachman, Joelle Pineau, Doina Precup, David Meger
2018	—	`conf`	Learning Invariances for Policy Generalization. ICLR (Workshop) Remi Tachet des Combes, Philip Bachman, Harm van Seijen
2018	J	`jnl`	Learning Invariances for Policy Generalization. CoRR Remi Tachet des Combes, Philip Bachman, Harm van Seijen
2018	J	`jnl`	VFunc: a Deep Generative Model for Functions. CoRR Philip Bachman, Riashat Islam, Alessandro Sordoni, Zafarali Ahmed
2017	—	`conf`	Calibrating Energy-based Generative Adversarial Networks. ICLR (Poster) Zihang Dai, Amjad Almahairi, Philip Bachman, Eduard H. Hovy, Aaron C. Courville
2017	J	`jnl`	Calibrating Energy-based Generative Adversarial Networks. CoRR Zihang Dai, Amjad Almahairi, Philip Bachman, Eduard H. Hovy, Aaron C. Courville
2017	J	`jnl`	Deep Reinforcement Learning that Matters. CoRR Peter Henderson, Riashat Islam, Philip Bachman, Joelle Pineau, Doina Precup, David Meger
2017	—	`conf`	Learning Algorithms for Active Learning. ICLR (Workshop) Philip Bachman, Alessandro Sordoni, Adam Trischler
2017	A*	`conf`	Learning Algorithms for Active Learning. ICML Philip Bachman, Alessandro Sordoni, Adam Trischler
2017	J	`jnl`	Learning Algorithms for Active Learning. CoRR Philip Bachman, Alessandro Sordoni, Adam Trischler
2017	—	`conf`	Machine Comprehension by Text-to-Text Neural Question Generation. Rep4NLP@ACL Xingdi Yuan, Tong Wang, Çaglar Gülçehre, Alessandro Sordoni, Philip Bachman, Saizheng Zhang, Sandeep Subramanian, Adam Trischler
2017	J	`jnl`	Machine Comprehension by Text-to-Text Neural Question Generation. CoRR Xingdi Yuan, Tong Wang, Çaglar Gülçehre, Alessandro Sordoni, Philip Bachman, Sandeep Subramanian, Saizheng Zhang, Adam Trischler
2017	—	`conf`	Natural Language Generation in Dialogue using Lexicalized and Delexicalized Data. ICLR (Workshop) Shikhar Sharma, Jing He, Kaheer Suleman, Hannes Schulz, Philip Bachman
2017	—	`conf`	NewsQA: A Machine Comprehension Dataset. Rep4NLP@ACL Adam Trischler, Tong Wang, Xingdi Yuan, Justin Harris, Alessandro Sordoni, Philip Bachman, Kaheer Suleman
2017	J	`jnl`	Variational Generative Stochastic Networks with Collaborative Shaping. CoRR Philip Bachman, Doina Precup
2016	—	`conf`	A Parallel-Hierarchical Model for Machine Comprehension on Sparse Data. ACL (1) Adam Trischler, Zheng Ye, Xingdi Yuan, Jing He, Philip Bachman
2016	J	`jnl`	A Parallel-Hierarchical Model for Machine Comprehension on Sparse Data. CoRR Adam Trischler, Zheng Ye, Xingdi Yuan, Jing He, Philip Bachman, Kaheer Suleman
2016	—	`conf`	An Architecture for Deep, Hierarchical Generative Models. NIPS Philip Bachman
2016	J	`jnl`	An Architecture for Deep, Hierarchical Generative Models. CoRR Philip Bachman
2016	J	`jnl`	Iterative Alternating Neural Attention for Machine Reading. CoRR Alessandro Sordoni, Philip Bachman, Yoshua Bengio
2016	A*	`conf`	Natural Language Comprehension with the EpiReader. EMNLP Adam Trischler, Zheng Ye, Xingdi Yuan, Philip Bachman, Alessandro Sordoni, Kaheer Suleman
2016	J	`jnl`	Natural Language Generation in Dialogue using Lexicalized and Delexicalized Data. CoRR Shikhar Sharma, Jing He, Kaheer Suleman, Hannes Schulz, Philip Bachman
2016	J	`jnl`	NewsQA: A Machine Comprehension Dataset. CoRR Adam Trischler, Tong Wang, Xingdi Yuan, Justin Harris, Alessandro Sordoni, Philip Bachman, Kaheer Suleman
2016	J	`jnl`	Towards Information-Seeking Agents. CoRR Philip Bachman, Alessandro Sordoni, Adam Trischler
2015	—	`conf`	Data Generation as Sequential Decision Making. NIPS Philip Bachman, Doina Precup
2015	J	`jnl`	Data Generation as Sequential Decision Making. CoRR Philip Bachman, Doina Precup
2015	J	`jnl`	Testing Visual Attention in Dynamic Environments. CoRR Philip Bachman, David Krueger, Doina Precup
2015	A*	`conf`	Variational Generative Stochastic Networks with Collaborative Shaping. ICML Philip Bachman, Doina Precup
2014	—	`conf`	Learning with Pseudo-Ensembles. NIPS Philip Bachman, Ouais Alsharif, Doina Precup
2014	J	`jnl`	Learning with Pseudo-Ensembles. CoRR Philip Bachman, Ouais Alsharif, Doina Precup
2014	J	`jnl`	Lifelong Learning of Discriminative Representations. CoRR Ouais Alsharif, Philip Bachman, Joelle Pineau
2014	A*	`conf`	Sample-based approximate regularization. ICML Philip Bachman, Amir-massoud Farahmand, Doina Precup
2013	—	`conf`	Greedy Confidence Pursuit: A Pragmatic Approach to Multi-bandit Optimization. ECML/PKDD (1) Philip Bachman, Doina Precup
2012	A*	`conf`	Improved Estimation in Time Varying Models. ICML Doina Precup, Philip Bachman
2011	A*	`conf`	Learning Compact Representations of Time-Varying Processes. AAAI Philip Bachman, Doina Precup
2009	J	`jnl`	Structure discovery in PPI networks using pattern-based network decomposition. Bioinform. Philip Bachman, Ying Liu