Pierre-Luc Bacon

86 papers A* 27A 3Journal 55Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinity. CoRR Aneri Muni, Vincent Taboga, Esther Derman, Pierre-Luc Bacon, Erick Delage
2026	J	`jnl`	Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models. CoRR Zhilong Zhang, Haoxiang Ren, Yihao Sun, Yifei Sheng, Haonan Wang, Haoxin Lin, Zhichao Wu, Pierre-Luc Bacon, Yang Yu
2026	J	`jnl`	What Makes Value Learning Efficient in Residual Reinforcement Learning? CoRR Guozheng Ma, Lu Li, Haoyu Wang, Zixuan Liu, Pierre-Luc Bacon, Dacheng Tao
2025	J	`jnl`	Discovery of Sustainable Refrigerants through Physics-Informed RL Fine-Tuning of Sequence Models. CoRR Adrien Goldszal, Diego Calanzone, Vincent Taboga, Pierre-Luc Bacon
2025	J	`jnl`	Long-Horizon Model-Based Offline Reinforcement Learning Without Conservatism. CoRR Tianwei Ni, Esther Derman, Vineet Jain, Vincent Taboga, Siamak Ravanbakhsh, Pierre-Luc Bacon
2025	A*	`conf`	MaestroMotif: Skill Design from Artificial Intelligence Feedback. ICLR Martin Klissarov, Mikael Henaff, Roberta Raileanu, Shagun Sodhani, Pascal Vincent, Amy Zhang, Pierre-Luc Bacon, Doina Precup, Marlos C. Machado, Pierluca D'Oro
2025	J	`jnl`	Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons. Trans. Mach. Learn. Res. Simon Dufort-Labbé, Pierluca D'Oro, Evgenii Nikishin, Irina Rish, Pierre-Luc Bacon, Razvan Pascanu, Aristide Baratin
2025	J	`jnl`	Mol-MoE: Training Preference-Guided Routers for Molecule Generation. CoRR Diego Calanzone, Pierluca D'Oro, Pierre-Luc Bacon
2025	A*	`conf`	Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning. ICML Guozheng Ma, Lu Li, Zilin Wang, Li Shen, Pierre-Luc Bacon, Dacheng Tao
2025	J	`jnl`	Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning. CoRR Guozheng Ma, Lu Li, Zilin Wang, Li Shen, Pierre-Luc Bacon, Dacheng Tao
2025	J	`jnl`	Planning with Unified Multimodal Models. CoRR Yihao Sun, Zhilong Zhang, Yang Yu, Pierre-Luc Bacon
2025	J	`jnl`	Robust Reinforcement Learning for Discrete Compositional Generation via General Soft Operators. CoRR Marco Jiralerspong, Esther Derman, Danilo Vucetic, Nikolay Malkin, Bilun Sun, Tianyu Zhang, Pierre-Luc Bacon, Gauthier Gidel
2025	A*	`conf`	Scaling Trends in Language Model Robustness. ICML Nikolaus H. R. Howe, Ian R. McKenzie, Oskar John Hollinsworth, Michal Zajac, Tom Tseng, Aaron David Tucker, Pierre-Luc Bacon, Adam Gleave
2025	J	`jnl`	Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning. CoRR Roger Creus Castanyer, Johan S. Obando-Ceron, Lu Li, Pierre-Luc Bacon, Glen Berseth, Aaron C. Courville, Pablo Samuel Castro
2025	J	`jnl`	State Entropy Regularization for Robust Reinforcement Learning. CoRR Yonatan Ashlag, Uri Koren, Mirco Mutti, Esther Derman, Pierre-Luc Bacon, Shie Mannor
2025	J	`jnl`	The Three Regimes of Offline-to-Online Reinforcement Learning. CoRR Lu Li, Tianwei Ni, Yihao Sun, Pierre-Luc Bacon
2025	J	`jnl`	Understanding Behavioral Metric Learning: A Large-Scale Study on Distracting Reinforcement Learning Environments. CoRR Ziyan Luo, Tianwei Ni, Pierre-Luc Bacon, Doina Precup, Xujie Si
2024	A*	`conf`	Bridging State and History Representations: Understanding Self-Predictive RL. ICLR Tianwei Ni, Benjamin Eysenbach, Erfan Seyedsalehi, Michel Ma, Clement Gehring, Aditya Mahajan, Pierre-Luc Bacon
2024	J	`jnl`	Bridging State and History Representations: Understanding Self-Predictive RL. CoRR Tianwei Ni, Benjamin Eysenbach, Erfan Seyedsalehi, Michel Ma, Clement Gehring, Aditya Mahajan, Pierre-Luc Bacon
2024	A*	`conf`	Course Correcting Koopman Representations. ICLR Mahan Fathi, Clement Gehring, Jonathan Pilault, David Kanaa, Pierre-Luc Bacon, Ross Goroshin
2024	A*	`conf`	Decoupling regularization from the action space. ICLR Sobhan Mohammadpour, Emma Frejinger, Pierre-Luc Bacon
2024	J	`jnl`	Decoupling regularization from the action space. CoRR Sobhan Mohammadpour, Emma Frejinger, Pierre-Luc Bacon
2024	A*	`conf`	Do Transformer World Models Give Better Policy Gradients? ICML Michel Ma, Tianwei Ni, Clement Gehring, Pierluca D'Oro, Pierre-Luc Bacon
2024	J	`jnl`	Do Transformer World Models Give Better Policy Gradients? CoRR Michel Ma, Tianwei Ni, Clement Gehring, Pierluca D'Oro, Pierre-Luc Bacon
2024	J	`jnl`	Exploring Scaling Trends in LLM Robustness. CoRR Nikolaus H. R. Howe, Michal Zajac, Ian R. McKenzie, Oskar John Hollinsworth, Tom Tseng, Pierre-Luc Bacon, Adam Gleave
2024	J	`jnl`	Generative Active Learning for the Search of Small-molecule Protein Binders. CoRR Maksym Korablyov, Cheng-Hao Liu, Moksh Jain, Almer M. van der Sloot, Eric Jolicoeur, Edward Ruediger, Andrei Cristian Nica, Emmanuel Bengio, Kostiantyn Lapchevskyi, Daniel St-Cyr, Doris Alexandra Schuetz, Victor Ion Butoi, Jarrid Rector-Brooks, Simon Blackburn, Leo Feng, Hadi Nekoei, Sai Krishna Gottipati, Priyesh Vijayan, Prateek Gupta, Ladislav Rampásek, Sasikanth Avancha, Pierre-Luc Bacon, William L. Hamilton, Brooks Paige, Sanchit Misra, Stanislaw Kamil Jastrzebski, Bharat Kaul, Doina Precup, José Miguel Hernández-Lobato, Marwin H. S. Segler, Michael M. Bronstein, Anne Marinier, Mike Tyers, Yoshua Bengio
2024	J	`jnl`	MaestroMotif: Skill Design from Artificial Intelligence Feedback. CoRR Martin Klissarov, Mikael Henaff, Roberta Raileanu, Shagun Sodhani, Pascal Vincent, Amy Zhang, Pierre-Luc Bacon, Doina Precup, Marlos C. Machado, Pierluca D'Oro
2024	A	`conf`	Maximum entropy GFlowNets with soft Q-learning. AISTATS Sobhan Mohammadpour, Emmanuel Bengio, Emma Frejinger, Pierre-Luc Bacon
2024	J	`jnl`	Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons. CoRR Simon Dufort-Labbé, Pierluca D'Oro, Evgenii Nikishin, Razvan Pascanu, Pierre-Luc Bacon, Aristide Baratin
2024	A*	`conf`	Motif: Intrinsic Motivation from Artificial Intelligence Feedback. ICLR Martin Klissarov, Pierluca D'Oro, Shagun Sodhani, Roberta Raileanu, Pierre-Luc Bacon, Pascal Vincent, Amy Zhang, Mikael Henaff
2023	J	`jnl`	Block-State Transformer. CoRR Mahan Fathi, Jonathan Pilault, Pierre-Luc Bacon, Christopher Pal, Orhan Firat, Ross Goroshin
2023	A*	`conf`	Block-State Transformers. NeurIPS Jonathan Pilault, Mahan Fathi, Orhan Firat, Chris Pal, Pierre-Luc Bacon, Ross Goroshin
2023	J	`jnl`	Course Correcting Koopman Representations. CoRR Mahan Fathi, Clement Gehring, Jonathan Pilault, David Kanaa, Pierre-Luc Bacon, Ross Goroshin
2023	A*	`conf`	Double Gumbel Q-Learning. NeurIPS David Yu-Tung Hui, Aaron C. Courville, Pierre-Luc Bacon
2023	J	`jnl`	Goal-conditioned GFlowNets for Controllable Multi-Objective Molecular Design. CoRR Julien Roy, Pierre-Luc Bacon, Christopher Pal, Emmanuel Bengio
2023	J	`jnl`	Maximum entropy GFlowNets with soft Q-learning. CoRR Sobhan Mohammadpour, Emmanuel Bengio, Emma Frejinger, Pierre-Luc Bacon
2023	J	`jnl`	Motif: Intrinsic Motivation from Artificial Intelligence Feedback. CoRR Martin Klissarov, Pierluca D'Oro, Shagun Sodhani, Roberta Raileanu, Pierre-Luc Bacon, Pascal Vincent, Amy Zhang, Mikael Henaff
2023	A*	`conf`	Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control. NeurIPS Nate Rahn, Pierluca D'Oro, Harley Wiltzer, Pierre-Luc Bacon, Marc G. Bellemare
2023	J	`jnl`	Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control. CoRR Nate Rahn, Pierluca D'Oro, Harley Wiltzer, Pierre-Luc Bacon, Marc G. Bellemare
2023	A*	`conf`	Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier. ICLR Pierluca D'Oro, Max Schwarzer, Evgenii Nikishin, Pierre-Luc Bacon, Marc G. Bellemare, Aaron C. Courville
2023	A*	`conf`	When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment. NeurIPS Tianwei Ni, Michel Ma, Benjamin Eysenbach, Pierre-Luc Bacon
2023	J	`jnl`	When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment. CoRR Tianwei Ni, Michel Ma, Benjamin Eysenbach, Pierre-Luc Bacon
2022	A*	`conf`	Continuous-Time Meta-Learning with Forward Mode Differentiation. ICLR Tristan Deleu, David Kanaa, Leo Feng, Giancarlo Kerg, Yoshua Bengio, Guillaume Lajoie, Pierre-Luc Bacon
2022	J	`jnl`	Continuous-Time Meta-Learning with Forward Mode Differentiation. CoRR Tristan Deleu, David Kanaa, Leo Feng, Giancarlo Kerg, Yoshua Bengio, Guillaume Lajoie, Pierre-Luc Bacon
2022	A*	`conf`	Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation. AAAI Evgenii Nikishin, Romina Abachi, Rishabh Agarwal, Pierre-Luc Bacon
2022	J	`jnl`	Designing Biological Sequences via Meta-Reinforcement Learning and Bayesian Optimization. CoRR Leo Feng, Padideh Nouri, Aneri Muni, Yoshua Bengio, Pierre-Luc Bacon
2022	A*	`conf`	Direct Behavior Specification via Constrained Reinforcement Learning. ICML Julien Roy, Roger Girgis, Joshua Romoff, Pierre-Luc Bacon, Christopher J. Pal
2022	A*	`conf`	Myriad: a real-world testbed to bridge trajectory optimization and deep learning. NeurIPS Nikolaus H. R. Howe, Simon Dufort-Labbé, Nitarshan Rajkumar, Pierre-Luc Bacon
2022	J	`jnl`	Myriad: a real-world testbed to bridge trajectory optimization and deep learning. CoRR Nikolaus H. R. Howe, Simon Dufort-Labbé, Nitarshan Rajkumar, Pierre-Luc Bacon
2022	A*	`conf`	The Primacy Bias in Deep Reinforcement Learning. ICML Evgenii Nikishin, Max Schwarzer, Pierluca D'Oro, Pierre-Luc Bacon, Aaron C. Courville
2022	J	`jnl`	The Primacy Bias in Deep Reinforcement Learning. CoRR Evgenii Nikishin, Max Schwarzer, Pierluca D'Oro, Pierre-Luc Bacon, Aaron C. Courville
2021	J	`jnl`	An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning. CoRR Dilip Arumugam, Peter Henderson, Pierre-Luc Bacon
2021	J	`jnl`	Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation. CoRR Evgenii Nikishin, Romina Abachi, Rishabh Agarwal, Pierre-Luc Bacon
2021	J	`jnl`	Direct Behavior Specification via Constrained Reinforcement Learning. CoRR Julien Roy, Roger Girgis, Joshua Romoff, Pierre-Luc Bacon, Christopher J. Pal
2021	A*	`conf`	Neural Algorithmic Reasoners are Implicit Planners. NeurIPS Andreea Deac, Petar Velickovic, Ognjen Milinkovic, Pierre-Luc Bacon, Jian Tang, Mladen Nikolic
2021	J	`jnl`	Neural Algorithmic Reasoners are Implicit Planners. CoRR Andreea Deac, Petar Velickovic, Ognjen Milinkovic, Pierre-Luc Bacon, Jian Tang, Mladen Nikolic
2021	A	`conf`	TDprop: Does Adaptive Optimization With Jacobi Preconditioning Help Temporal Difference Learning? AAMAS Joshua Romoff, Peter Henderson, David Kanaa, Emmanuel Bengio, Ahmed Touati, Pierre-Luc Bacon, Joelle Pineau
2020	J	`jnl`	Graph neural induction of value iteration. CoRR Andreea Deac, Pierre-Luc Bacon, Jian Tang
2020	A*	`conf`	Options of Interest: Temporal Abstraction with Interest Functions. AAAI Khimya Khetarpal, Martin Klissarov, Maxime Chevalier-Boisvert, Pierre-Luc Bacon, Doina Precup
2020	J	`jnl`	Options of Interest: Temporal Abstraction with Interest Functions. CoRR Khimya Khetarpal, Martin Klissarov, Maxime Chevalier-Boisvert, Pierre-Luc Bacon, Doina Precup
2020	J	`jnl`	Policy Evaluation Networks. CoRR Jean Harb, Tom Schaul, Doina Precup, Pierre-Luc Bacon
2020	J	`jnl`	TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning? CoRR Joshua Romoff, Peter Henderson, David Kanaa, Emmanuel Bengio, Ahmed Touati, Pierre-Luc Bacon, Joelle Pineau
2020	A*	`conf`	Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling. ICML Yao Liu, Pierre-Luc Bacon, Emma Brunskill
2020	J	`jnl`	XLVIN: eXecuted Latent Value Iteration Nets. CoRR Andreea Deac, Petar Velickovic, Ognjen Milinkovic, Pierre-Luc Bacon, Jian Tang, Mladen Nikolic
2019	J	`jnl`	All-Action Policy Gradient Methods: A Numerical Integration Approach. CoRR Benjamin Petit, Loren Amdahl-Culleton, Yao Liu, Jimmy Smith, Pierre-Luc Bacon
2019	J	`jnl`	Entropy Regularization with Discounted Future State Distribution in Policy Gradient Methods. CoRR Riashat Islam, Raihan Seraj, Pierre-Luc Bacon, Doina Precup
2019	J	`jnl`	Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling. CoRR Yao Liu, Pierre-Luc Bacon, Emma Brunskill
2018	J	`jnl`	Constructing Temporal Abstractions Autonomously in Reinforcement Learning. AI Mag. Pierre-Luc Bacon, Doina Precup
2018	A*	`conf`	Convergent TREE BACKUP and RETRACE with Function Approximation. ICML Ahmed Touati, Pierre-Luc Bacon, Doina Precup, Pascal Vincent
2018	A*	`conf`	Learning Robust Options. AAAI Daniel J. Mankowitz, Timothy A. Mann, Pierre-Luc Bacon, Doina Precup, Shie Mannor
2018	J	`jnl`	Learning Robust Options. CoRR Daniel J. Mankowitz, Timothy A. Mann, Pierre-Luc Bacon, Doina Precup, Shie Mannor
2018	A*	`conf`	Learning With Options That Terminate Off-Policy. AAAI Anna Harutyunyan, Peter Vrancx, Pierre-Luc Bacon, Doina Precup, Ann Nowé
2018	A*	`conf`	OptionGAN: Learning Joint Reward-Policy Options Using Generative Adversarial Inverse Reinforcement Learning. AAAI Peter Henderson, Wei-Di Chang, Pierre-Luc Bacon, David Meger, Joelle Pineau, Doina Precup
2018	J	`jnl`	The Barbados 2018 List of Open Issues in Continual Learning. CoRR Tom Schaul, Hado van Hasselt, Joseph Modayil, Martha White, Adam White, Pierre-Luc Bacon, Jean Harb, Shibl Mourad, Marc G. Bellemare, Doina Precup
2018	A*	`conf`	When Waiting Is Not an Option: Learning Options With a Deliberation Cost. AAAI Jean Harb, Pierre-Luc Bacon, Martin Klissarov, Doina Precup
2017	J	`jnl`	Convergent Tree-Backup and Retrace with Function Approximation. CoRR Ahmed Touati, Pierre-Luc Bacon, Doina Precup, Pascal Vincent
2017	J	`jnl`	Learning with Options that Terminate Off-Policy. CoRR Anna Harutyunyan, Peter Vrancx, Pierre-Luc Bacon, Doina Precup, Ann Nowé
2017	J	`jnl`	Learnings Options End-to-End for Continuous Action Tasks. CoRR Martin Klissarov, Pierre-Luc Bacon, Jean Harb, Doina Precup
2017	J	`jnl`	OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning. CoRR Peter Henderson, Wei-Di Chang, Pierre-Luc Bacon, David Meger, Joelle Pineau, Doina Precup
2017	A*	`conf`	The Option-Critic Architecture. AAAI Pierre-Luc Bacon, Jean Harb, Doina Precup
2017	J	`jnl`	When Waiting is not an Option : Learning Options with a Deliberation Cost. CoRR Jean Harb, Pierre-Luc Bacon, Martin Klissarov, Doina Precup
2016	J	`jnl`	A Matrix Splitting Perspective on Planning with Options. CoRR Pierre-Luc Bacon, Doina Precup
2016	J	`jnl`	The Option-Critic Architecture. CoRR Pierre-Luc Bacon, Jean Harb, Doina Precup
2015	—	`conf`	Analyzing Open Data from the City of Montreal. MUD@ICML Joelle Pineau, Pierre-Luc Bacon
2015	J	`jnl`	Conditional Computation in Neural Networks for faster models. CoRR Emmanuel Bengio, Pierre-Luc Bacon, Joelle Pineau, Doina Precup
2015	A	`conf`	Learning and Planning with Timing Information in Markov Decision Processes. UAI Pierre-Luc Bacon, Borja Balle, Doina Precup