Bernardo Ávila Pires

36 papers A* 11A 1Journal 21Unranked 3

Year	Rank	Type	Title / Venue / Authors
2025	A	`conf`	A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning. AISTATS Khimya Khetarpal, Zhaohan Daniel Guo, Bernardo Ávila Pires, Yunhao Tang, Clare Lyle, Mark Rowland, Nicolas Heess, Diana L. Borsa, Arthur Guez, Will Dabney
2025	J	`jnl`	Optimizing Return Distributions with Distributional Dynamic Programming. CoRR Bernardo Ávila Pires, Mark Rowland, Diana Borsa, Zhaohan Daniel Guo, Khimya Khetarpal, André Barreto, David Abel, Rémi Munos, Will Dabney
2025	J	`jnl`	Optimizing Return Distributions with Distributional Dynamic Programming. J. Mach. Learn. Res. Bernardo Ávila Pires, Mark Rowland, Diana Borsa, Zhaohan Daniel Guo, Khimya Khetarpal, André Barreto, David Abel, Rémi Munos, Will Dabney
2025	J	`jnl`	Representation Learning via Non-Contrastive Mutual Information. CoRR Zhaohan Daniel Guo, Bernardo Ávila Pires, Khimya Khetarpal, Dale Schuurmans, Bo Dai
2024	J	`jnl`	A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning. CoRR Khimya Khetarpal, Zhaohan Daniel Guo, Bernardo Ávila Pires, Yunhao Tang, Clare Lyle, Mark Rowland, Nicolas Heess, Diana Borsa, Arthur Guez, Will Dabney
2024	A*	`conf`	Generalized Preference Optimization: A Unified Approach to Offline Alignment. ICML Yunhao Tang, Zhaohan Daniel Guo, Zeyu Zheng, Daniele Calandriello, Rémi Munos, Mark Rowland, Pierre Harvey Richemond, Michal Valko, Bernardo Ávila Pires, Bilal Piot
2024	J	`jnl`	Generalized Preference Optimization: A Unified Approach to Offline Alignment. CoRR Yunhao Tang, Zhaohan Daniel Guo, Zeyu Zheng, Daniele Calandriello, Rémi Munos, Mark Rowland, Pierre Harvey Richemond, Michal Valko, Bernardo Ávila Pires, Bilal Piot
2024	A*	`conf`	Human Alignment of Large Language Models through Online Preference Optimisation. ICML Daniele Calandriello, Zhaohan Daniel Guo, Rémi Munos, Mark Rowland, Yunhao Tang, Bernardo Ávila Pires, Pierre Harvey Richemond, Charline Le Lan, Michal Valko, Tianqi Liu, Rishabh Joshi, Zeyu Zheng, Bilal Piot
2024	J	`jnl`	Human Alignment of Large Language Models through Online Preference Optimisation. CoRR Daniele Calandriello, Daniel Guo, Rémi Munos, Mark Rowland, Yunhao Tang, Bernardo Ávila Pires, Pierre Harvey Richemond, Charline Le Lan, Michal Valko, Tianqi Liu, Rishabh Joshi, Zeyu Zheng, Bilal Piot
2024	J	`jnl`	Off-policy Distributional Q(λ): Distributional RL without Importance Sampling. CoRR Yunhao Tang, Mark Rowland, Rémi Munos, Bernardo Ávila Pires, Will Dabney
2024	J	`jnl`	Offline Regularised Reinforcement Learning for Large Language Models Alignment. CoRR Pierre Harvey Richemond, Yunhao Tang, Daniel Guo, Daniele Calandriello, Mohammad Gheshlaghi Azar, Rafael Rafailov, Bernardo Ávila Pires, Eugene Tarassov, Lucas Spangher, Will Ellsworth, Aliaksei Severyn, Jonathan Mallinson, Lior Shani, Gil Shamir, Rishabh Joshi, Tianqi Liu, Rémi Munos, Bilal Piot
2024	J	`jnl`	Understanding the performance gap between online and offline alignment algorithms. CoRR Yunhao Tang, Zhaohan Daniel Guo, Zeyu Zheng, Daniele Calandriello, Yuan Cao, Eugene Tarassov, Rémi Munos, Bernardo Ávila Pires, Michal Valko, Yong Cheng, Will Dabney
2023	A*	`conf`	DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm. ICML Yunhao Tang, Tadashi Kozuno, Mark Rowland, Anna Harutyunyan, Rémi Munos, Bernardo Ávila Pires, Michal Valko
2023	J	`jnl`	DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm. CoRR Yunhao Tang, Tadashi Kozuno, Mark Rowland, Anna Harutyunyan, Rémi Munos, Bernardo Ávila Pires, Michal Valko
2023	J	`jnl`	Hierarchical Reinforcement Learning in Complex 3D Environments. CoRR Bernardo Ávila Pires, Feryal M. P. Behbahani, Hubert Soyer, Kyriacos Nikiforou, Thomas Keck, Satinder Singh
2023	A*	`conf`	Understanding Plasticity in Neural Networks. ICML Clare Lyle, Zeyu Zheng, Evgenii Nikishin, Bernardo Ávila Pires, Razvan Pascanu, Will Dabney
2023	A*	`conf`	Understanding Self-Predictive Learning for Reinforcement Learning. ICML Yunhao Tang, Zhaohan Daniel Guo, Pierre Harvey Richemond, Bernardo Ávila Pires, Yash Chandak, Rémi Munos, Mark Rowland, Mohammad Gheshlaghi Azar, Charline Le Lan, Clare Lyle, András György, Shantanu Thakoor, Will Dabney, Bilal Piot, Daniele Calandriello, Michal Valko
2023	J	`jnl`	Understanding plasticity in neural networks. CoRR Clare Lyle, Zeyu Zheng, Evgenii Nikishin, Bernardo Ávila Pires, Razvan Pascanu, Will Dabney
2022	A*	`conf`	BYOL-Explore: Exploration by Bootstrapped Prediction. NeurIPS Zhaohan Guo, Shantanu Thakoor, Miruna Pislar, Bernardo Ávila Pires, Florent Altché, Corentin Tallec, Alaa Saade, Daniele Calandriello, Jean-Bastien Grill, Yunhao Tang, Michal Valko, Rémi Munos, Mohammad Gheshlaghi Azar, Bilal Piot
2022	J	`jnl`	BYOL-Explore: Exploration by Bootstrapped Prediction. CoRR Zhaohan Daniel Guo, Shantanu Thakoor, Miruna Pislar, Bernardo Ávila Pires, Florent Altché, Corentin Tallec, Alaa Saade, Daniele Calandriello, Jean-Bastien Grill, Yunhao Tang, Michal Valko, Rémi Munos, Mohammad Gheshlaghi Azar, Bilal Piot
2022	A*	`conf`	The Nature of Temporal Difference Errors in Multi-step Distributional Reinforcement Learning. NeurIPS Yunhao Tang, Rémi Munos, Mark Rowland, Bernardo Ávila Pires, Will Dabney, Marc G. Bellemare
2022	J	`jnl`	The Nature of Temporal Difference Errors in Multi-step Distributional Reinforcement Learning. CoRR Yunhao Tang, Mark Rowland, Rémi Munos, Bernardo Ávila Pires, Will Dabney, Marc G. Bellemare
2022	J	`jnl`	Understanding Self-Predictive Learning for Reinforcement Learning. CoRR Yunhao Tang, Zhaohan Daniel Guo, Pierre Harvey Richemond, Bernardo Ávila Pires, Yash Chandak, Rémi Munos, Mark Rowland, Mohammad Gheshlaghi Azar, Charline Le Lan, Clare Lyle, András György, Shantanu Thakoor, Will Dabney, Bilal Piot, Daniele Calandriello, Michal Valko
2021	J	`jnl`	Geometric Entropic Exploration. CoRR Zhaohan Daniel Guo, Mohammad Gheshlaghi Azar, Alaa Saade, Shantanu Thakoor, Bilal Piot, Bernardo Ávila Pires, Michal Valko, Thomas Mesnard, Tor Lattimore, Rémi Munos
2021	J	`jnl`	Neural Recursive Belief States in Multi-Agent Reinforcement Learning. CoRR Pol Moreno, Edward Hughes, Kevin R. McKee, Bernardo Ávila Pires, Théophane Weber
2020	A*	`conf`	Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning. ICML Zhaohan Daniel Guo, Bernardo Ávila Pires, Bilal Piot, Jean-Bastien Grill, Florent Altché, Rémi Munos, Mohammad Gheshlaghi Azar
2020	J	`jnl`	Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning. CoRR Zhaohan Daniel Guo, Bernardo Ávila Pires, Bilal Piot, Jean-Bastien Grill, Florent Altché, Rémi Munos, Mohammad Gheshlaghi Azar
2020	A*	`conf`	Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning. NeurIPS Jean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre H. Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Ávila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, Rémi Munos, Michal Valko
2020	J	`jnl`	Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning. CoRR Jean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre H. Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Ávila Pires, Zhaohan Daniel Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, Rémi Munos, Michal Valko
2016	J	`jnl`	Multiclass Classification Calibration Functions. CoRR Bernardo Ávila Pires, Csaba Szepesvári
2016	A*	`conf`	Policy Error Bounds for Model-Based Reinforcement Learning with Factored Linear Models. COLT Bernardo Ávila Pires
2016	J	`jnl`	Policy Error Bounds for Model-Based Reinforcement Learning with Factored Linear Models. CoRR Bernardo Ávila Pires, Csaba Szepesvári
2015	—	`conf`	Pathological Effects of Variance on Classification-Based Policy Iteration. AAAI Workshop: Learning for General Competency in Video Games Bernardo Ávila Pires, Csaba Szepesvári
2014	—	`conf`	Pseudo-MDPs and factored linear action models. ADPRL Hengshuai Yao, Csaba Szepesvári, Bernardo Ávila Pires, Xinhua Zhang
2013	—	`conf`	Cost-sensitive Multiclass Classification Risk Bounds. ICML (3) Bernardo Ávila Pires, Csaba Szepesvári, Mohammad Ghavamzadeh
2012	A*	`conf`	Statistical linear estimation with penalized estimators: an application to reinforcement learning. ICML Bernardo Ávila Pires, Csaba Szepesvári