2019
The Option Keyboard: Combining Skills in Reinforcement
Learning
André Barreto, Diana Borsa, Shaobo Hou, Gheorghe Comanici, Eser Aygün, Philippe Hamel, Daniel Toyama, Jonathan J. Hunt, Shibl Mourad, David Silver, Doina Precup
In Advances in Neural Information Processing Systems (NeurIPS)
[ pdf ] [ video ] [ slides ] [ poster ] [ more info ]Universal Successor Features Approximators
Diana Borsa, André Barreto, John Quan, Daniel Mankowitz, Rémi Munos, Hado van Hasselt, David Silver, Tom Schaul
In Proceedings of the International Conference on Learning Representations (ICLR)
[ pdf ] [ video 1 ] [ video 2 ] [ more info ]Composing Entropic Policies Using Divergence Correction
Jonathan Hunt, André Barreto, Timothy Lillicrap, Nicolas Heess
In Proceedings of International Conference on Machine Learning (ICML)
[ pdf ] [ videos ] [ more info ]Fast Task Inference with Variational Intrinsic Successor
Features
Steven Hansen, Will Dabney, André Barreto, Tom Van de
Wiele, David Warde-Farley, Volodymyr Mnih
arXiv
[ pdf ] [ more info ]Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates
Carlos Riquelme, Hugo Penedones, Damien Vincent, Hartmut Maennel, Sylvain Gelly, Timothy A. Mann, Andre Barreto, Gergely Neu
In Advances in Neural Information Processing Systems (NeurIPS)
[ pdf ] [ poster ] [ more info ]General Non-linear Bellman equations
Hado van Hasselt, John Quan, Matteo Hessel, Zhongwen Xu, Diana Borsa, Andre Barreto
The Multi-disciplinary Conference on Reinforcement
Learning and Decision Making (RLDM)
[ pdf ] [ more info ]Graph-Based Skill Acquisition for Reinforcement Learning
Matheus Mendonça, Artur Ziviani, André Barreto
ACM Computing Surveys, 52 (1)
[ more info ]2018
Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement
André Barreto, Diana Borsa, John Quan, Tom Schaul, David Silver, Matteo Hessel, Daniel Mankowitz, Augustin Žídek, Rémi Munos
In Proceedings of the International Conference on Machine Learning (ICML)
[ pdf ] [ video ] [ slides 1 ] [ slides 2 ] [ poster ] [ more info ]Fast Deep Reinforcement Learning Using Online Adjustments from the Past
Steven Hansen, Alexander Pritzel, Pablo Sprechmann, André Barreto, Charles Blundell
In Advances in Neural Information Processing Systems (NeurIPS)
[ pdf ] [ more info ]Online TD(lambda) for discrete-time Markov jump linear
systems
Rafael Beirigo, Marcos Todorov, André Barreto
In Proceedings of the IEEE Annual Conference on Decision and Control (CDC)
[ more info ] Temporal Difference Learning with Neural Networks -
Study of the Leakage Propagation Problem
Hugo Penedones, Damien Vincent, Hartmut Maennel, Sylvain Gelly, Timothy Mann, André Barreto
arXiv
[ pdf ] [ more info ] Unicorn: Continual Learning with a Universal,
Off-Policy, Agent
Daniel J Mankowitz, Augustin Žídek, André Barreto, Dan Horgan, Matteo Hessel, John Quan, Junhyuk Oh, Hado van Hasselt, David Silver, Tom Schaul
The Multi-disciplinary Conference on Reinforcement
Learning and Decision Making (RLDM)
[ pdf ] [ more info ]Abstract State Transition Graphs for Model-Based Reinforcement Learning
Matheus Mendonça, Artur Ziviani, André Barreto
In Proceedings of the Brazilian Conference on
Intelligent Systems (BRACIS)
[ more
info ]2017
Successor Features for Transfer in Reinforcement Learning
André Barreto, Will Dabney, Rémi Munos, Jonathan J. Hunt, Tom Schaul, Hado van Hasselt, David Silver
In Advances in Neural Information Processing Systems (NIPS) - selected as a spotlight
[ pdf ] [ slides ] [poster ] [ workshop version ] [ more info ]The Predictron: End-to-end Learning and Planning
David Silver, Hado van Hasselt, Matteo Hessel, Tom Schaul, Arthur Guez, Tim Harley, Gabriel Dulac-Arnold, David P. Reichert, Neil C. Rabinowitz, André Barreto, Thomas Degris
In Proceedings of the International Conference on Machine Learning, (ICML)
[ pdf ] [ video ] [ more info ]Natural Value Approximators: Learning When to Trust Past Estimates
Zhongwen Xu, Joseph Modayil, Hado van Hasselt, André Barreto, David Silver, Tom Schaul
In Advances in Neural Information Processing Systems (NIPS) - selected as a spotlight
[ pdf ] [ more info ]Value-Aware Loss Function for Model-based Reinforcement Learning
Amir-Massoud Farahmand, André Barreto, Daniel Nikovski
In Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)
[ pdf ] [ more info ]Count-Based Quadratic Control of Markov Jump Linear Systems with Unknown Transition Probabilities
Rafael Beirigo, Marcos Todorov, André Barreto
In Proceedings of the IEEE Annual Conference on Decision and Control (CDC)
[ more info ]Transfer on Count-based Quadratic Control of Markov Jump Linear Systems with Unknown Transition Probabilities
Rafael Beirigo, Marcos Todorov, André Barreto
In Proceedings of Conferência Brasileira de Dinâmica, Controle e Aplicações (DINCON)
[ pdf ]2016
Practical Kernel-Based Reinforcement Learning
André Barreto, Doina Precup, Joelle Pineau
Journal of Machine Learning Research, v. 17 (67), pp. 1−70
[ pdf ] [ more info ]Incremental Stochastic Factorization for Online Reinforcement Learning
André Barreto, Rafael L. Beirigo, Joelle Pineau, Doina Precup
In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)
[ pdf ] [ more info ]2015
An Expectation-Maximization Algorithm to Compute a Stochastic Factorization From Data
André Barreto, Rafael L. Beirigo, Joelle Pineau, Doina Precup
In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)
[ pdf ] [ more info ]Classification-based Approximate Policy Iteration
Amir-massoud Farahmand, Doina Precup, André Barreto, Mohammad Ghavamzadeh
IEEE Transactions on Automatic Control, v. 60 (12)[ pdf ] [ more info ]
2014
Policy Iteration Based on Stochastic Factorization
André Barreto, Joelle Pineau, Doina Precup
Journal of Artificial Intelligence Research, v. 50, pp. 763−803[ pdf ] [ more info ]