ML robuste, adaptatif et modulaire | Montréal

debug-gym: A Text-Based Environment for Interactive Debugging

Xingdi Yuan, Morgane M Moss, Charbel Feghali, Chinmay Singh, Darya Moldavskaya, Drew MacPhee, Lucas Caccia, Matheus Pereira, Minseon Kim, Alessandro Sordoni, Marc-Alexandre Côté

March 2025

Publication

A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning

Prateek Yadav, Colin Raffel, Mohammed Muqeeth, Lucas Caccia, Haokun Liu, Tian-Xiang Chen, Mohit Bansal, Leshem Choshen, Alessandro Sordoni

ArXiv | August 2024, Vol abs/2408.07057

DOI Publication Publication

Multi-Head Adapter Routing for Data-Efficient Fine-Tuning

Lucas Caccia, E. Ponti, Lu Liu, Matheus Pereira, Nicolas Le Roux, Alessandro Sordoni

ArXiv | November 2023, Vol abs/2211.03831

DOI Publication Publication

Measuring the Carbon Intensity of AI in Cloud Instances

Remi Tachet des Combes, Erika Odmark, Will Buchanan

ACM Conference on Fairness, Accountability, and Transparency | June 2022

Publication Project

A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms

Shangtong Zhang, Romain Laroche, Harm van Seijen, Shimon Whiteson, Remi Tachet des Combes

International Conference on Autonomous Agents and Multiagent Systems (AAMAS) | May 2022

Publication Project

Better Language Model with Hypernym Class Prediction

He Bai, Tong Wang, Alessandro Sordoni, Peng Shi

ACL 2022 | May 2022

Publication

Unsupervised Dependency Graph Network

Yikang Shen, Shawn Tan, Alessandro Sordoni, Peng Li, Jie Zhou, Aaron Courville

ACL 2022 | May 2022

Publication

Evaluating Distributional Distortion in Neural Language Modeling

Benjamin LeBrun, Alessandro Sordoni, Timothy J. O’Donnell

ICLR 2022 | April 2022

Publication

Learning to Dequantise with Truncated Flows

Shawn Tan, Chin-Wei Huang, Alessandro Sordoni, Aaron Courville

ICLR 2022 | April 2022

Publication

Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms

Romain Laroche, Remi Tachet des Combes

AISTATS 2022 | March 2022

Publication Project

A general class of surrogate functions for stable and efficient reinforcement learning

Sharan Vaswani, Olivier Bachem, Simone Totaro, Robert Müller, Shivam Garg, Matthieu Geist, Marlos C. Machado, Pablo Samuel Castro, Nicolas Le Roux

2022 International Conference on Artificial Intelligence and Statistics | March 2022

Publication

Collaborative Exploration and Exploitation in massively Multi-Player Bandits

Hiba Dakdouk, Raphaël Féraud, Nadège Varsier, Patrick Maillé, Romain Laroche

March 2022

Publication

On the Convergence of Stochastic Extragradient for Bilinear Games using Restarted Iteration Averaging

Chris Junchi Li, Yaodong Yu, Nicolas Loizou, Gauthier Gidel, Yi Ma, Nicolas Le Roux, Michael I. Jordan

2022 International Conference on Artificial Intelligence and Statistics | March 2022

Publication

On the Chattering of SARSA with Linear Function Approximation

Shangtong Zhang, Romain Laroche, Remi Tachet des Combes

February 2022

Publication Project

A single gradient step finds adversarial examples on random two-layers neural networks

Sébastien Bubeck, Yeshwanth Cherapanamjeri, Gauthier Gidel, Remi Tachet des Combes

NeurIPS 2021 | December 2021

Publication

Dr Jekyll & Mr Hyde: the strange case of off-policy policy updates

Romain Laroche, Remi Tachet des Combes

NeurIPS 2021 | December 2021

Publication Project

Pretraining Representations for Data-Efficient Reinforcement Learning

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

NeurIPS 2021 | December 2021

Publication

Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU

Meghana Moorthy Bhat, Alessandro Sordoni, Subhabrata (Subho) Mukherjee

EMNLP 2021 | November 2021

Publication Project Project

The emergence of the shape bias results from communicative efficiency

Eva Portelance, Michael C. Frank, Dan Jurafsky, Alessandro Sordoni, Romain Laroche

Conference on Computational Natural Language Learning (CoNLL) | November 2021

Publication

Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs

Harsh Satija, Philip S. Thomas, Joelle Pineau, Romain Laroche

2021 Neural Information Processing Systems | October 2021

Publication Project

Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch

Shangtong Zhang, Remi Tachet des Combes, Romain Laroche

October 2021

Publication Project

Batched Bandits with Crowd Externalities

Romain Laroche, Othmane Safsafi, Raphaël Féraud, Nicolas Broutin

September 2021

Publication

Decomposed Mutual Information Estimation for Contrastive Representation Learning

Alessandro Sordoni, Nouha Dziri, Hannes Schulz, Geoff Gordon, Philip Bachman, Remi Tachet des Combes

2021 International Conference on Machine Learning | July 2021

Publication

Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents

Rui Meng, Khushboo Thaker, Lei Zhang, Yue Dong, Xingdi Yuan, Tong Wang, Daqing He

ACL-IJCNLP 2021 | May 2021

Publication

Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle

Yikang Shen, Shawn Tan, Alessandro Sordoni, Siva Reddy, Aaron Courville

May 2021

Publication

Understanding by Understanding Not: Modeling Negation in Language Models

Arian Hosseini, Siva Reddy, Dzmitry Bahdanau, Devon Hjelm, Alessandro Sordoni, Aaron Courville

May 2021

PDF

Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks

Sungryull Sohn, Sungtae Lee, Jongwook Choi, Harm van Seijen, Honglak Lee, Mehdi Fatemi

2021 International Conference on Machine Learning | May 2021

Publication Publication

Learning to Represent Action Values as a Hypergraph on the Action Vertices

Arash Tavakoli, Mehdi Fatemi, Petar Kormushev

2021 International Conference on Learning Representations (ICLR’21) | May 2021

PDF PDF Publication Publication

Linguistic dependencies and statistical dependence

Jacob Louis Hoover, Alessandro Sordoni, Wenyu Du, Timothy J. O’Donnell

2021 Empirical Methods in Natural Language Processing | April 2021

Publication

Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift

Remi Tachet des Combes, Han Zhao, Yu-Xiang Wang, Geoff Gordon

NeurIPS | December 2020

PDF Github

Deep Reinforcement and InfoMax Learning

Bogdan Mazoure, Remi Tachet des Combes, Thang Long Doan, Philip Bachman, Devon Hjelm

NeurIPS 2020 | December 2020

Publication

Learning Dynamic Belief Graphs to Generalize on Text-Based Games

Ashutosh Adhikari, Xingdi Yuan, Marc-Alexandre Côté, Mikulas Zelinka, Marc-Antoine Rondeau, Romain Laroche, Pascal Poupart, Jian Tang, Adam Trischler, William L. Hamilton

NeurIPS 2020 | October 2020

PDF

Adversarial score matching and improved sampling for image generation

Alexia Jolicoeur-Martineau, Rémi Piché-Taillefer, Remi Tachet des Combes, Ioannis Mitliagkas

September 2020

Publication

Representation Learning with Video Deep InfoMax

Devon Hjelm, Philip Bachman

July 2020

PDF

Data-Efficient Reinforcement Learning with Momentum Predictive Representations

Max Schwarzer, Ankesh Anand, Rishab Goel, Devon Hjelm, Aaron Courville, Philip Bachman

July 2020

PDF

Reinforcement Learning Framework for Deep Brain Stimulation Study

Dmitrii Krylov, Remi Tachet des Combes, Romain Laroche, Michael Rosenblum, Dmitry V. Dylov

International Joint Conference on Artificial Intelligence | July 2020

Publication

A Reduction from Reinforcement Learning to No-Regret Online Learning

Ching-An Cheng, Remi Tachet des Combes, Byron Boots, Geoff Gordon

International Conference on Artificial Intelligence and Statistics | June 2020

Publication

Safe Policy Improvement with an Estimated Baseline Policy

Thiago D. Simao, Romain Laroche, Remi Tachet des Combes

International Conference on Autonomous Agents and Multi-Agent Systems | May 2020

Publication Project

Exploring and Predicting Transferability Across NLP Tasks

Tu Vu, Tong Wang, Tsendsuren Munkhdalai, Alessandro Sordoni, Adam Trischler, Andrew Mattarella-Micke, Subhransu Maji, Mohit Iyyer

May 2020

Publication

Fast Domain Adaptation For Goal-Oriented Dialogue Using A Hybrid Generative-Retrieval Transformer

Igor Shalyminov, Alessandro Sordoni, Adam Atkinson, Hannes Schulz

2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | April 2020

Publication Download Project

Hybrid Generative-Retrieval Transformers For Dialogue Domain Adaptation

Igor Shalyminov, Alessandro Sordoni, Adam Atkinson, Hannes Schulz

arXiv preprint arXiv:2003.01680 | March 2020

PDF Project

Population Histories of the United States Revealed through Fine-Scale Migration and Haplotype Analysis

Chengzhen L. Dai, Mohammad M. Vazifeh, Chen-Hsiang Yeang, Remi Tachet des Combes, R. Spencer Wells, Miguel G. Vilar, Mark J. Daly, Carlo Ratti, Alicia R. Martin

The American Journal of Human Genetics | March 2020, Vol 106(3): pp. 371-388

Publication

Report on the First HIPstIR Workshop on the Future of Information Retrieval

Laura Dietz, Bhaskar Mitra, Jeremy Pickens, Hana Anber, Sandeep Avula, Asia J. Biega, Adrian Boteanu, Shubham Chatterjee, Jeff Dalton, Shiri Dori-Hacohen, John Foley, Henry Feild, Ben Gamari, Rosie Jones, Pallika Kanani, Sumanta Kashyapi, Widad Machmouchi, Matthew Mitsui, Steve Nole, Alexandre Tachard Passos, Jordan Ramsdell, Adam Roegiest, David Smith, Alessandro Sordoni

SIGIR Forum | December 2019, Vol 53(2): pp. 62-75

Publication

Utilisation d’une cartographie logarithmique pour permettre des facteurs de réduction plus faibles dans l’apprentissage de renforcement

Harm van Seijen, Mehdi Fatemi, Arash Tavakoli

Neural Information Processing Systems (NeurIPS) | December 2019

Oral Presentation

PDF

Ordered Memory

Yikang Shen, Shawn Tan, Arian Hosseini, Zhouhan Lin, Alessandro Sordoni, Aaron Courville

NeurIPS 2019 | November 2019

ArXiv

Publication

Robust Natural Language Inference Models with Example Forgetting

Yadollah Yaghoobzadeh, Remi Tachet des Combes, T. J. Hazen, Alessandro Sordoni

November 2019

Publication

Safe Policy Improvement with Soft Baseline Bootstrapping

Kimia Nadjahi, Romain Laroche, Remi Tachet des Combes

European Conference in Machine Learning (ECML-PKDD) | September 2019

Publication Project

Metalearned Neural Memory

Tsendsuren Munkhdalai, Alessandro Sordoni, Tong Wang, Adam Trischler

NeurIPS 2019 | July 2019

Preprint under review

Publication

Multi-batch Reinforcement Learning

Romain Laroche, Remi Tachet des Combes

The 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM) | July 2019

Publication

SPIBB-DQN: Safe Batch Reinforcement Learning with Function Approximation

Romain Laroche, Remi Tachet des Combes

The 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM) | July 2019

Publication

Learning Representations by Maximizing Mutual Information Across Views

Philip Bachman, Devon Hjelm, William Buchwalter

June 2019

PDF Publication Github

Dead-ends and Secure Exploration in Reinforcement Learning

Mehdi Fatemi, Shikhar Sharma, Harm van Seijen, Samira Ebrahimi Kahou

Proceedings of the 36th International Conference on Machine Learning (ICML) | June 2019

Spotlight Presentation

Publication Github

On Learning Invariant Representation for Domain Adaptation

Han Zhao, Remi Tachet des Combes, Kun Zhang, Geoff Gordon

International Conference on Machine Learning | June 2019

Publication

On the Learning Dynamics of Deep Neural Networks

Remi Tachet des Combes

ICML – Theoretical Physics for Deep Learning Workshop | June 2019

Publication

Rapport bref : Neurones commandés : Intégration des structures d’arbres dans les réseaux neuronaux récurrents

Yikeng Shen, Shawn Tan, Alessandro Sordoni, Aaron Courville

ICLR 2019 | May 2019

ICLR 2019 Best Paper Award

Publication

An Empirical Study of Example Forgetting during Deep Neural Network Learning

Mariya Toneva, Alessandro Sordoni, Remi Tachet des Combes, Adam Trischler, Yoshua Bengio, Geoff Gordon

ICLR 2019 | April 2019

Publication

Apprendre des représentations profondes par l’estimation et la maximisation de l’information mutuelle

Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Philip Bachman, Adam Trischler, Yoshua Bengio

ICLR 2019 | April 2019

Publication

Towards Text Generation with Adversarially Learned Neural Outlines

Sandeep Subramanian, Sai Rajeswar, Alessandro Sordoni, Adam Trischler, Aaron Courville, Christopher Pal

NeurIPS 2018 | December 2018

Publication Project

Counting to Explore and Generalize in Text-based Games

Xingdi Yuan, Marc-Alexandre Côté, Alessandro Sordoni, Romain Laroche, Remi Tachet des Combes, Matthew Hausknecht, Adam Trischler

European Workshop on Reinforcement Learning (EWRL) | October 2018

Publication Project

Training Dialogue Systems With Human Advice

Merwan Barlier, Romain Laroche, Olivier Pietquin

Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems (AAMAS) | July 2018

Publication

Straight to the Tree: Constituency Parsing with Neural Syntactic Distance

Yikang Shen, Zhouhan Lin, Athul Paul Jacob, Alessandro Sordoni, Aaron Courville, Yoshua Bengio

Proceedings of ACL | July 2018

PDF

Augmented cyclegan: Learning many-to-many mappings from unpaired data

Amjad Almahairi, Sai Rajeswar, Alessandro Sordoni, Philip Bachman, Aaron Courville

ICML 2018 | June 2018

ArXiv

Publication

Focused Hierarchical RNNs for Conditional Sequence Processing

Nan Rosemary Ke, Konrad Zolna, Alessandro Sordoni, Zhouhan Lin, Adam Trischler, Yoshua Bengio, Joelle Pineau, Laurent Charlin, Chris Pal

ICML 2018 | June 2018

Publication Project

In reinforcement learning, all objective functions are not equal

Romain Laroche, Harm van Seijen

Proceedings of the 6th International Conference on Learning Representations (ICLR) – workshop track | May 2018

Publication

Reinforcement Learning Algorithm Selection

Romain Laroche, Raphael Feraud

Proceedings of the 6th International Conference on Learning Representations (ICLR) | May 2018

Publication

On Value Function Representation of Long Horizon Problems

Lucas Lehnert, Romain Laroche, Harm van Seijen

Proceedings of the 33rd AAAI international conference | February 2018

Publication

Twin Networks: Matching the Future for Sequence Generation

Dmitriy Serdyuk, Nan Rosemary Ke, Alessandro Sordoni, Chris Pal, Adam Trischler, Yoshua Bengio

ICLR 2018 | January 2018

Publication Project

debug-gym: A Text-Based Environment for Interactive Debugging

Xingdi Yuan, Morgane M Moss, Charbel Feghali, Chinmay Singh, Darya Moldavskaya, Drew MacPhee, Lucas Caccia, Matheus Pereira, Minseon Kim, Alessandro Sordoni, Marc-Alexandre Côté

March 2025

Publication

A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning

Prateek Yadav, Colin Raffel, Mohammed Muqeeth, Lucas Caccia, Haokun Liu, Tian-Xiang Chen, Mohit Bansal, Leshem Choshen, Alessandro Sordoni

ArXiv | August 2024, Vol abs/2408.07057

DOI Publication Publication

Multi-Head Adapter Routing for Data-Efficient Fine-Tuning

Lucas Caccia, E. Ponti, Lu Liu, Matheus Pereira, Nicolas Le Roux, Alessandro Sordoni

ArXiv | November 2023, Vol abs/2211.03831

DOI Publication Publication

Measuring the Carbon Intensity of AI in Cloud Instances

Remi Tachet des Combes, Erika Odmark, Will Buchanan

ACM Conference on Fairness, Accountability, and Transparency | June 2022

Publication Project

A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms

Shangtong Zhang, Romain Laroche, Harm van Seijen, Shimon Whiteson, Remi Tachet des Combes

International Conference on Autonomous Agents and Multiagent Systems (AAMAS) | May 2022

Publication Project

Learning to Dequantise with Truncated Flows

Shawn Tan, Chin-Wei Huang, Alessandro Sordoni, Aaron Courville

ICLR 2022 | April 2022

Publication

Evaluating Distributional Distortion in Neural Language Modeling

Benjamin LeBrun, Alessandro Sordoni, Timothy J. O’Donnell

ICLR 2022 | April 2022

Publication

Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms

Romain Laroche, Remi Tachet des Combes

AISTATS 2022 | March 2022

Publication Project

Collaborative Exploration and Exploitation in massively Multi-Player Bandits

Hiba Dakdouk, Raphaël Féraud, Nadège Varsier, Patrick Maillé, Romain Laroche

March 2022

Publication

A general class of surrogate functions for stable and efficient reinforcement learning

Sharan Vaswani, Olivier Bachem, Simone Totaro, Robert Müller, Shivam Garg, Matthieu Geist, Marlos C. Machado, Pablo Samuel Castro, Nicolas Le Roux

2022 International Conference on Artificial Intelligence and Statistics | March 2022

Publication

On the Chattering of SARSA with Linear Function Approximation

Shangtong Zhang, Romain Laroche, Remi Tachet des Combes

February 2022

Publication Project

Dr Jekyll & Mr Hyde: the strange case of off-policy policy updates

Romain Laroche, Remi Tachet des Combes

NeurIPS 2021 | December 2021

Publication Project

Pretraining Representations for Data-Efficient Reinforcement Learning

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

NeurIPS 2021 | December 2021

Publication

A single gradient step finds adversarial examples on random two-layers neural networks

Sébastien Bubeck, Yeshwanth Cherapanamjeri, Gauthier Gidel, Remi Tachet des Combes

NeurIPS 2021 | December 2021

Publication

The emergence of the shape bias results from communicative efficiency

Eva Portelance, Michael C. Frank, Dan Jurafsky, Alessandro Sordoni, Romain Laroche

Conference on Computational Natural Language Learning (CoNLL) | November 2021

Publication

Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs

Harsh Satija, Philip S. Thomas, Joelle Pineau, Romain Laroche

2021 Neural Information Processing Systems | October 2021

Publication Project

Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch

Shangtong Zhang, Remi Tachet des Combes, Romain Laroche

October 2021

Publication Project

Batched Bandits with Crowd Externalities

Romain Laroche, Othmane Safsafi, Raphaël Féraud, Nicolas Broutin

September 2021

Publication

Decomposed Mutual Information Estimation for Contrastive Representation Learning

Alessandro Sordoni, Nouha Dziri, Hannes Schulz, Geoff Gordon, Philip Bachman, Remi Tachet des Combes

2021 International Conference on Machine Learning | July 2021

Publication

Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents

Rui Meng, Khushboo Thaker, Lei Zhang, Yue Dong, Xingdi Yuan, Tong Wang, Daqing He

ACL-IJCNLP 2021 | May 2021

Publication

Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle

Yikang Shen, Shawn Tan, Alessandro Sordoni, Siva Reddy, Aaron Courville

May 2021

Publication

Understanding by Understanding Not: Modeling Negation in Language Models

Arian Hosseini, Siva Reddy, Dzmitry Bahdanau, Devon Hjelm, Alessandro Sordoni, Aaron Courville

May 2021

PDF

Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks

Sungryull Sohn, Sungtae Lee, Jongwook Choi, Harm van Seijen, Honglak Lee, Mehdi Fatemi

2021 International Conference on Machine Learning | May 2021

Publication Publication

Learning to Represent Action Values as a Hypergraph on the Action Vertices

Arash Tavakoli, Mehdi Fatemi, Petar Kormushev

2021 International Conference on Learning Representations (ICLR’21) | May 2021

PDF PDF Publication Publication

Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift

Remi Tachet des Combes, Han Zhao, Yu-Xiang Wang, Geoff Gordon

NeurIPS | December 2020

PDF Github

Deep Reinforcement and InfoMax Learning

Bogdan Mazoure, Remi Tachet des Combes, Thang Long Doan, Philip Bachman, Devon Hjelm

NeurIPS 2020 | December 2020

Publication

Learning Dynamic Belief Graphs to Generalize on Text-Based Games

Ashutosh Adhikari, Xingdi Yuan, Marc-Alexandre Côté, Mikulas Zelinka, Marc-Antoine Rondeau, Romain Laroche, Pascal Poupart, Jian Tang, Adam Trischler, William L. Hamilton

NeurIPS 2020 | October 2020

PDF

Data-Efficient Reinforcement Learning with Momentum Predictive Representations

Max Schwarzer, Ankesh Anand, Rishab Goel, Devon Hjelm, Aaron Courville, Philip Bachman

July 2020

PDF

Reinforcement Learning Framework for Deep Brain Stimulation Study

Dmitrii Krylov, Remi Tachet des Combes, Romain Laroche, Michael Rosenblum, Dmitry V. Dylov

International Joint Conference on Artificial Intelligence | July 2020

Publication

A Reduction from Reinforcement Learning to No-Regret Online Learning

Ching-An Cheng, Remi Tachet des Combes, Byron Boots, Geoff Gordon

International Conference on Artificial Intelligence and Statistics | June 2020

Publication

Safe Policy Improvement with an Estimated Baseline Policy

Thiago D. Simao, Romain Laroche, Remi Tachet des Combes

International Conference on Autonomous Agents and Multi-Agent Systems | May 2020

Publication Project

Hybrid Generative-Retrieval Transformers For Dialogue Domain Adaptation

Igor Shalyminov, Alessandro Sordoni, Adam Atkinson, Hannes Schulz

arXiv preprint arXiv:2003.01680 | March 2020

PDF Project

Report on the First HIPstIR Workshop on the Future of Information Retrieval

Laura Dietz, Bhaskar Mitra, Jeremy Pickens, Hana Anber, Sandeep Avula, Asia J. Biega, Adrian Boteanu, Shubham Chatterjee, Jeff Dalton, Shiri Dori-Hacohen, John Foley, Henry Feild, Ben Gamari, Rosie Jones, Pallika Kanani, Sumanta Kashyapi, Widad Machmouchi, Matthew Mitsui, Steve Nole, Alexandre Tachard Passos, Jordan Ramsdell, Adam Roegiest, David Smith, Alessandro Sordoni

SIGIR Forum | December 2019, Vol 53(2): pp. 62-75

Publication

Utilisation d’une cartographie logarithmique pour permettre des facteurs de réduction plus faibles dans l’apprentissage de renforcement

Harm van Seijen, Mehdi Fatemi, Arash Tavakoli

Neural Information Processing Systems (NeurIPS) | December 2019

Oral Presentation

PDF

Robust Natural Language Inference Models with Example Forgetting

Yadollah Yaghoobzadeh, Remi Tachet des Combes, T. J. Hazen, Alessandro Sordoni

November 2019

Publication

Ordered Memory

Yikang Shen, Shawn Tan, Arian Hosseini, Zhouhan Lin, Alessandro Sordoni, Aaron Courville

NeurIPS 2019 | November 2019

ArXiv

Publication

Safe Policy Improvement with Soft Baseline Bootstrapping

Kimia Nadjahi, Romain Laroche, Remi Tachet des Combes

European Conference in Machine Learning (ECML-PKDD) | September 2019

Publication Project

Metalearned Neural Memory

Tsendsuren Munkhdalai, Alessandro Sordoni, Tong Wang, Adam Trischler

NeurIPS 2019 | July 2019

Preprint under review

Publication

SPIBB-DQN: Safe Batch Reinforcement Learning with Function Approximation

Romain Laroche, Remi Tachet des Combes

The 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM) | July 2019

Publication

Multi-batch Reinforcement Learning

Romain Laroche, Remi Tachet des Combes

The 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM) | July 2019

Publication

Learning Representations by Maximizing Mutual Information Across Views

Philip Bachman, Devon Hjelm, William Buchwalter

June 2019

PDF Publication Github

On the Learning Dynamics of Deep Neural Networks

Remi Tachet des Combes

ICML – Theoretical Physics for Deep Learning Workshop | June 2019

Publication

On Learning Invariant Representation for Domain Adaptation

Han Zhao, Remi Tachet des Combes, Kun Zhang, Geoff Gordon

International Conference on Machine Learning | June 2019

Publication

Dead-ends and Secure Exploration in Reinforcement Learning

Mehdi Fatemi, Shikhar Sharma, Harm van Seijen, Samira Ebrahimi Kahou

Proceedings of the 36th International Conference on Machine Learning (ICML) | June 2019

Spotlight Presentation

Publication Github

Rapport bref : Neurones commandés : Intégration des structures d’arbres dans les réseaux neuronaux récurrents

Yikeng Shen, Shawn Tan, Alessandro Sordoni, Aaron Courville

ICLR 2019 | May 2019

ICLR 2019 Best Paper Award

Publication

Apprendre des représentations profondes par l’estimation et la maximisation de l’information mutuelle

Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Philip Bachman, Adam Trischler, Yoshua Bengio

ICLR 2019 | April 2019

Publication

An Empirical Study of Example Forgetting during Deep Neural Network Learning

Mariya Toneva, Alessandro Sordoni, Remi Tachet des Combes, Adam Trischler, Yoshua Bengio, Geoff Gordon

ICLR 2019 | April 2019

Publication

Towards Text Generation with Adversarially Learned Neural Outlines

Sandeep Subramanian, Sai Rajeswar, Alessandro Sordoni, Adam Trischler, Aaron Courville, Christopher Pal

NeurIPS 2018 | December 2018

Publication Project

Counting to Explore and Generalize in Text-based Games

Xingdi Yuan, Marc-Alexandre Côté, Alessandro Sordoni, Romain Laroche, Remi Tachet des Combes, Matthew Hausknecht, Adam Trischler

European Workshop on Reinforcement Learning (EWRL) | October 2018

Publication Project

Training Dialogue Systems With Human Advice

Merwan Barlier, Romain Laroche, Olivier Pietquin

Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems (AAMAS) | July 2018

Publication

Straight to the Tree: Constituency Parsing with Neural Syntactic Distance

Yikang Shen, Zhouhan Lin, Athul Paul Jacob, Alessandro Sordoni, Aaron Courville, Yoshua Bengio

Proceedings of ACL | July 2018

PDF

Focused Hierarchical RNNs for Conditional Sequence Processing

Nan Rosemary Ke, Konrad Zolna, Alessandro Sordoni, Zhouhan Lin, Adam Trischler, Yoshua Bengio, Joelle Pineau, Laurent Charlin, Chris Pal

ICML 2018 | June 2018

Publication Project

Augmented cyclegan: Learning many-to-many mappings from unpaired data

Amjad Almahairi, Sai Rajeswar, Alessandro Sordoni, Philip Bachman, Aaron Courville

ICML 2018 | June 2018

ArXiv

Publication

In reinforcement learning, all objective functions are not equal

Romain Laroche, Harm van Seijen

Proceedings of the 6th International Conference on Learning Representations (ICLR) – workshop track | May 2018

Publication

Reinforcement Learning Algorithm Selection

Romain Laroche, Raphael Feraud

Proceedings of the 6th International Conference on Learning Representations (ICLR) | May 2018

Publication

On Value Function Representation of Long Horizon Problems

Lucas Lehnert, Romain Laroche, Harm van Seijen

Proceedings of the 33rd AAAI international conference | February 2018

Publication

Twin Networks: Matching the Future for Sequence Generation

Dmitriy Serdyuk, Nan Rosemary Ke, Alessandro Sordoni, Chris Pal, Adam Trischler, Yoshua Bengio

ICLR 2018 | January 2018

Publication Project

debug-gym: A Text-Based Environment for Interactive Debugging

Xingdi Yuan, Morgane M Moss, Charbel Feghali, Chinmay Singh, Darya Moldavskaya, Drew MacPhee, Lucas Caccia, Matheus Pereira, Minseon Kim, Alessandro Sordoni, Marc-Alexandre Côté

March 2025

Publication

Measuring the Carbon Intensity of AI in Cloud Instances

Remi Tachet des Combes, Erika Odmark, Will Buchanan

ACM Conference on Fairness, Accountability, and Transparency | June 2022

Publication Project

Unsupervised Dependency Graph Network

Yikang Shen, Shawn Tan, Alessandro Sordoni, Peng Li, Jie Zhou, Aaron Courville

ACL 2022 | May 2022

Publication

Better Language Model with Hypernym Class Prediction

He Bai, Tong Wang, Alessandro Sordoni, Peng Shi

ACL 2022 | May 2022

Publication

Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU

Meghana Moorthy Bhat, Alessandro Sordoni, Subhabrata (Subho) Mukherjee

EMNLP 2021 | November 2021

Publication Project Project

Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents

Rui Meng, Khushboo Thaker, Lei Zhang, Yue Dong, Xingdi Yuan, Tong Wang, Daqing He

ACL-IJCNLP 2021 | May 2021

Publication

Understanding by Understanding Not: Modeling Negation in Language Models

Arian Hosseini, Siva Reddy, Dzmitry Bahdanau, Devon Hjelm, Alessandro Sordoni, Aaron Courville

May 2021

PDF

Linguistic dependencies and statistical dependence

Jacob Louis Hoover, Alessandro Sordoni, Wenyu Du, Timothy J. O’Donnell

2021 Empirical Methods in Natural Language Processing | April 2021

Publication

Exploring and Predicting Transferability Across NLP Tasks

Tu Vu, Tong Wang, Tsendsuren Munkhdalai, Alessandro Sordoni, Adam Trischler, Andrew Mattarella-Micke, Subhransu Maji, Mohit Iyyer

May 2020

Publication

On the Convergence of Stochastic Extragradient for Bilinear Games using Restarted Iteration Averaging

Chris Junchi Li, Yaodong Yu, Nicolas Loizou, Gauthier Gidel, Yi Ma, Nicolas Le Roux, Michael I. Jordan

2022 International Conference on Artificial Intelligence and Statistics | March 2022

Publication

A single gradient step finds adversarial examples on random two-layers neural networks

Sébastien Bubeck, Yeshwanth Cherapanamjeri, Gauthier Gidel, Remi Tachet des Combes

NeurIPS 2021 | December 2021

Publication

Adversarial score matching and improved sampling for image generation

Alexia Jolicoeur-Martineau, Rémi Piché-Taillefer, Remi Tachet des Combes, Ioannis Mitliagkas

September 2020

Publication

Representation Learning with Video Deep InfoMax

Devon Hjelm, Philip Bachman

July 2020

PDF

Population Histories of the United States Revealed through Fine-Scale Migration and Haplotype Analysis

Chengzhen L. Dai, Mohammad M. Vazifeh, Chen-Hsiang Yeang, Remi Tachet des Combes, R. Spencer Wells, Miguel G. Vilar, Mark J. Daly, Carlo Ratti, Alicia R. Martin

The American Journal of Human Genetics | March 2020, Vol 106(3): pp. 371-388

Publication

Fast Domain Adaptation For Goal-Oriented Dialogue Using A Hybrid Generative-Retrieval Transformer

Igor Shalyminov, Alessandro Sordoni, Adam Atkinson, Hannes Schulz

2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | April 2020

Publication Download Project

Learning Dynamic Belief Graphs to Generalize on Text-Based Games

Ashutosh Adhikari, Xingdi Yuan, Marc-Alexandre Côté, Mikulas Zelinka, Marc-Antoine Rondeau, Romain Laroche, Pascal Poupart, Jian Tang, Adam Trischler, William L. Hamilton

NeurIPS 2020 | October 2020

PDF

Report on the First HIPstIR Workshop on the Future of Information Retrieval

Laura Dietz, Bhaskar Mitra, Jeremy Pickens, Hana Anber, Sandeep Avula, Asia J. Biega, Adrian Boteanu, Shubham Chatterjee, Jeff Dalton, Shiri Dori-Hacohen, John Foley, Henry Feild, Ben Gamari, Rosie Jones, Pallika Kanani, Sumanta Kashyapi, Widad Machmouchi, Matthew Mitsui, Steve Nole, Alexandre Tachard Passos, Jordan Ramsdell, Adam Roegiest, David Smith, Alessandro Sordoni

SIGIR Forum | December 2019, Vol 53(2): pp. 62-75

Publication

debug-gym: A Text-Based Environment for Interactive Debugging

Xingdi Yuan, Morgane M Moss, Charbel Feghali, Chinmay Singh, Darya Moldavskaya, Drew MacPhee, Lucas Caccia, Matheus Pereira, Minseon Kim, Alessandro Sordoni, Marc-Alexandre Côté

March 2025

Publication

Collaborative Exploration and Exploitation in massively Multi-Player Bandits

Hiba Dakdouk, Raphaël Féraud, Nadège Varsier, Patrick Maillé, Romain Laroche

March 2022

Publication

On the Chattering of SARSA with Linear Function Approximation

Shangtong Zhang, Romain Laroche, Remi Tachet des Combes

February 2022

Publication Project

Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch

Shangtong Zhang, Remi Tachet des Combes, Romain Laroche

October 2021

Publication Project

Batched Bandits with Crowd Externalities

Romain Laroche, Othmane Safsafi, Raphaël Féraud, Nicolas Broutin

September 2021

Publication

Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle

Yikang Shen, Shawn Tan, Alessandro Sordoni, Siva Reddy, Aaron Courville

May 2021

Publication

Understanding by Understanding Not: Modeling Negation in Language Models

Arian Hosseini, Siva Reddy, Dzmitry Bahdanau, Devon Hjelm, Alessandro Sordoni, Aaron Courville

May 2021

PDF

Adversarial score matching and improved sampling for image generation

Alexia Jolicoeur-Martineau, Rémi Piché-Taillefer, Remi Tachet des Combes, Ioannis Mitliagkas

September 2020

Publication

Representation Learning with Video Deep InfoMax

Devon Hjelm, Philip Bachman

July 2020

PDF

Data-Efficient Reinforcement Learning with Momentum Predictive Representations

Max Schwarzer, Ankesh Anand, Rishab Goel, Devon Hjelm, Aaron Courville, Philip Bachman

July 2020

PDF

Exploring and Predicting Transferability Across NLP Tasks

Tu Vu, Tong Wang, Tsendsuren Munkhdalai, Alessandro Sordoni, Adam Trischler, Andrew Mattarella-Micke, Subhransu Maji, Mohit Iyyer

May 2020

Publication

Robust Natural Language Inference Models with Example Forgetting

Yadollah Yaghoobzadeh, Remi Tachet des Combes, T. J. Hazen, Alessandro Sordoni

November 2019

Publication

Learning Representations by Maximizing Mutual Information Across Views

Philip Bachman, Devon Hjelm, William Buchwalter

June 2019

PDF Publication Github

A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning

Prateek Yadav, Colin Raffel, Mohammed Muqeeth, Lucas Caccia, Haokun Liu, Tian-Xiang Chen, Mohit Bansal, Leshem Choshen, Alessandro Sordoni

ArXiv | August 2024, Vol abs/2408.07057

DOI Publication Publication

Multi-Head Adapter Routing for Data-Efficient Fine-Tuning

Lucas Caccia, E. Ponti, Lu Liu, Matheus Pereira, Nicolas Le Roux, Alessandro Sordoni

ArXiv | November 2023, Vol abs/2211.03831

DOI Publication Publication

Population Histories of the United States Revealed through Fine-Scale Migration and Haplotype Analysis

Chengzhen L. Dai, Mohammad M. Vazifeh, Chen-Hsiang Yeang, Remi Tachet des Combes, R. Spencer Wells, Miguel G. Vilar, Mark J. Daly, Carlo Ratti, Alicia R. Martin

The American Journal of Human Genetics | March 2020, Vol 106(3): pp. 371-388

Publication

Hybrid Generative-Retrieval Transformers For Dialogue Domain Adaptation

Igor Shalyminov, Alessandro Sordoni, Adam Atkinson, Hannes Schulz

arXiv preprint arXiv:2003.01680 | March 2020

PDF Project

Report on the First HIPstIR Workshop on the Future of Information Retrieval

Laura Dietz, Bhaskar Mitra, Jeremy Pickens, Hana Anber, Sandeep Avula, Asia J. Biega, Adrian Boteanu, Shubham Chatterjee, Jeff Dalton, Shiri Dori-Hacohen, John Foley, Henry Feild, Ben Gamari, Rosie Jones, Pallika Kanani, Sumanta Kashyapi, Widad Machmouchi, Matthew Mitsui, Steve Nole, Alexandre Tachard Passos, Jordan Ramsdell, Adam Roegiest, David Smith, Alessandro Sordoni

SIGIR Forum | December 2019, Vol 53(2): pp. 62-75

Publication

Straight to the Tree: Constituency Parsing with Neural Syntactic Distance

Yikang Shen, Zhouhan Lin, Athul Paul Jacob, Alessandro Sordoni, Aaron Courville, Yoshua Bengio

Proceedings of ACL | July 2018

PDF

Measuring the Carbon Intensity of AI in Cloud Instances

Remi Tachet des Combes, Erika Odmark, Will Buchanan

ACM Conference on Fairness, Accountability, and Transparency | June 2022

Publication Project

Unsupervised Dependency Graph Network

Yikang Shen, Shawn Tan, Alessandro Sordoni, Peng Li, Jie Zhou, Aaron Courville

ACL 2022 | May 2022

Publication

Better Language Model with Hypernym Class Prediction

He Bai, Tong Wang, Alessandro Sordoni, Peng Shi

ACL 2022 | May 2022

Publication

A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms

Shangtong Zhang, Romain Laroche, Harm van Seijen, Shimon Whiteson, Remi Tachet des Combes

International Conference on Autonomous Agents and Multiagent Systems (AAMAS) | May 2022

Publication Project

Learning to Dequantise with Truncated Flows

Shawn Tan, Chin-Wei Huang, Alessandro Sordoni, Aaron Courville

ICLR 2022 | April 2022

Publication

Evaluating Distributional Distortion in Neural Language Modeling

Benjamin LeBrun, Alessandro Sordoni, Timothy J. O’Donnell

ICLR 2022 | April 2022

Publication

Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms

Romain Laroche, Remi Tachet des Combes

AISTATS 2022 | March 2022

Publication Project

On the Convergence of Stochastic Extragradient for Bilinear Games using Restarted Iteration Averaging

Chris Junchi Li, Yaodong Yu, Nicolas Loizou, Gauthier Gidel, Yi Ma, Nicolas Le Roux, Michael I. Jordan

2022 International Conference on Artificial Intelligence and Statistics | March 2022

Publication

A general class of surrogate functions for stable and efficient reinforcement learning

Sharan Vaswani, Olivier Bachem, Simone Totaro, Robert Müller, Shivam Garg, Matthieu Geist, Marlos C. Machado, Pablo Samuel Castro, Nicolas Le Roux

2022 International Conference on Artificial Intelligence and Statistics | March 2022

Publication

Dr Jekyll & Mr Hyde: the strange case of off-policy policy updates

Romain Laroche, Remi Tachet des Combes

NeurIPS 2021 | December 2021

Publication Project

Pretraining Representations for Data-Efficient Reinforcement Learning

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

NeurIPS 2021 | December 2021

Publication

A single gradient step finds adversarial examples on random two-layers neural networks

Sébastien Bubeck, Yeshwanth Cherapanamjeri, Gauthier Gidel, Remi Tachet des Combes

NeurIPS 2021 | December 2021

Publication

The emergence of the shape bias results from communicative efficiency

Eva Portelance, Michael C. Frank, Dan Jurafsky, Alessandro Sordoni, Romain Laroche

Conference on Computational Natural Language Learning (CoNLL) | November 2021

Publication

Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU

Meghana Moorthy Bhat, Alessandro Sordoni, Subhabrata (Subho) Mukherjee

EMNLP 2021 | November 2021

Publication Project Project

Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs

Harsh Satija, Philip S. Thomas, Joelle Pineau, Romain Laroche

2021 Neural Information Processing Systems | October 2021

Publication Project

Decomposed Mutual Information Estimation for Contrastive Representation Learning

Alessandro Sordoni, Nouha Dziri, Hannes Schulz, Geoff Gordon, Philip Bachman, Remi Tachet des Combes

2021 International Conference on Machine Learning | July 2021

Publication

Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents

Rui Meng, Khushboo Thaker, Lei Zhang, Yue Dong, Xingdi Yuan, Tong Wang, Daqing He

ACL-IJCNLP 2021 | May 2021

Publication

Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks

Sungryull Sohn, Sungtae Lee, Jongwook Choi, Harm van Seijen, Honglak Lee, Mehdi Fatemi

2021 International Conference on Machine Learning | May 2021

Publication Publication

Learning to Represent Action Values as a Hypergraph on the Action Vertices

Arash Tavakoli, Mehdi Fatemi, Petar Kormushev

2021 International Conference on Learning Representations (ICLR’21) | May 2021

PDF PDF Publication Publication

Linguistic dependencies and statistical dependence

Jacob Louis Hoover, Alessandro Sordoni, Wenyu Du, Timothy J. O’Donnell

2021 Empirical Methods in Natural Language Processing | April 2021

Publication

Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift

Remi Tachet des Combes, Han Zhao, Yu-Xiang Wang, Geoff Gordon

NeurIPS | December 2020

PDF Github

Deep Reinforcement and InfoMax Learning

Bogdan Mazoure, Remi Tachet des Combes, Thang Long Doan, Philip Bachman, Devon Hjelm

NeurIPS 2020 | December 2020

Publication

Learning Dynamic Belief Graphs to Generalize on Text-Based Games

Ashutosh Adhikari, Xingdi Yuan, Marc-Alexandre Côté, Mikulas Zelinka, Marc-Antoine Rondeau, Romain Laroche, Pascal Poupart, Jian Tang, Adam Trischler, William L. Hamilton

NeurIPS 2020 | October 2020

PDF

Reinforcement Learning Framework for Deep Brain Stimulation Study

Dmitrii Krylov, Remi Tachet des Combes, Romain Laroche, Michael Rosenblum, Dmitry V. Dylov

International Joint Conference on Artificial Intelligence | July 2020

Publication

A Reduction from Reinforcement Learning to No-Regret Online Learning

Ching-An Cheng, Remi Tachet des Combes, Byron Boots, Geoff Gordon

International Conference on Artificial Intelligence and Statistics | June 2020

Publication

Safe Policy Improvement with an Estimated Baseline Policy

Thiago D. Simao, Romain Laroche, Remi Tachet des Combes

International Conference on Autonomous Agents and Multi-Agent Systems | May 2020

Publication Project

Fast Domain Adaptation For Goal-Oriented Dialogue Using A Hybrid Generative-Retrieval Transformer

Igor Shalyminov, Alessandro Sordoni, Adam Atkinson, Hannes Schulz

2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | April 2020

Publication Download Project

Utilisation d’une cartographie logarithmique pour permettre des facteurs de réduction plus faibles dans l’apprentissage de renforcement

Harm van Seijen, Mehdi Fatemi, Arash Tavakoli

Neural Information Processing Systems (NeurIPS) | December 2019

Oral Presentation

PDF

Ordered Memory

Yikang Shen, Shawn Tan, Arian Hosseini, Zhouhan Lin, Alessandro Sordoni, Aaron Courville

NeurIPS 2019 | November 2019

ArXiv

Publication

Safe Policy Improvement with Soft Baseline Bootstrapping

Kimia Nadjahi, Romain Laroche, Remi Tachet des Combes

European Conference in Machine Learning (ECML-PKDD) | September 2019

Publication Project

Metalearned Neural Memory

Tsendsuren Munkhdalai, Alessandro Sordoni, Tong Wang, Adam Trischler

NeurIPS 2019 | July 2019

Preprint under review

Publication

SPIBB-DQN: Safe Batch Reinforcement Learning with Function Approximation

Romain Laroche, Remi Tachet des Combes

The 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM) | July 2019

Publication

Multi-batch Reinforcement Learning

Romain Laroche, Remi Tachet des Combes

The 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM) | July 2019

Publication

On the Learning Dynamics of Deep Neural Networks

Remi Tachet des Combes

ICML – Theoretical Physics for Deep Learning Workshop | June 2019

Publication

On Learning Invariant Representation for Domain Adaptation

Han Zhao, Remi Tachet des Combes, Kun Zhang, Geoff Gordon

International Conference on Machine Learning | June 2019

Publication

Dead-ends and Secure Exploration in Reinforcement Learning

Mehdi Fatemi, Shikhar Sharma, Harm van Seijen, Samira Ebrahimi Kahou

Proceedings of the 36th International Conference on Machine Learning (ICML) | June 2019

Spotlight Presentation

Publication Github

Rapport bref : Neurones commandés : Intégration des structures d’arbres dans les réseaux neuronaux récurrents

Yikeng Shen, Shawn Tan, Alessandro Sordoni, Aaron Courville

ICLR 2019 | May 2019

ICLR 2019 Best Paper Award

Publication

Apprendre des représentations profondes par l’estimation et la maximisation de l’information mutuelle

Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Philip Bachman, Adam Trischler, Yoshua Bengio

ICLR 2019 | April 2019

Publication

An Empirical Study of Example Forgetting during Deep Neural Network Learning

Mariya Toneva, Alessandro Sordoni, Remi Tachet des Combes, Adam Trischler, Yoshua Bengio, Geoff Gordon

ICLR 2019 | April 2019

Publication

Towards Text Generation with Adversarially Learned Neural Outlines

Sandeep Subramanian, Sai Rajeswar, Alessandro Sordoni, Adam Trischler, Aaron Courville, Christopher Pal

NeurIPS 2018 | December 2018

Publication Project

Counting to Explore and Generalize in Text-based Games

Xingdi Yuan, Marc-Alexandre Côté, Alessandro Sordoni, Romain Laroche, Remi Tachet des Combes, Matthew Hausknecht, Adam Trischler

European Workshop on Reinforcement Learning (EWRL) | October 2018

Publication Project

Training Dialogue Systems With Human Advice

Merwan Barlier, Romain Laroche, Olivier Pietquin

Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems (AAMAS) | July 2018

Publication

Focused Hierarchical RNNs for Conditional Sequence Processing

Nan Rosemary Ke, Konrad Zolna, Alessandro Sordoni, Zhouhan Lin, Adam Trischler, Yoshua Bengio, Joelle Pineau, Laurent Charlin, Chris Pal

ICML 2018 | June 2018

Publication Project

Augmented cyclegan: Learning many-to-many mappings from unpaired data

Amjad Almahairi, Sai Rajeswar, Alessandro Sordoni, Philip Bachman, Aaron Courville

ICML 2018 | June 2018

ArXiv

Publication

In reinforcement learning, all objective functions are not equal

Romain Laroche, Harm van Seijen

Proceedings of the 6th International Conference on Learning Representations (ICLR) – workshop track | May 2018

Publication

Reinforcement Learning Algorithm Selection

Romain Laroche, Raphael Feraud

Proceedings of the 6th International Conference on Learning Representations (ICLR) | May 2018

Publication

On Value Function Representation of Long Horizon Problems

Lucas Lehnert, Romain Laroche, Harm van Seijen

Proceedings of the 33rd AAAI international conference | February 2018

Publication

Twin Networks: Matching the Future for Sequence Generation

Dmitriy Serdyuk, Nan Rosemary Ke, Alessandro Sordoni, Chris Pal, Adam Trischler, Yoshua Bengio

ICLR 2018 | January 2018

Publication Project