Alert button
Picture for Andre Barreto

Andre Barreto

Alert button

Video as the New Language for Real-World Decision Making

Feb 27, 2024
Sherry Yang, Jacob Walker, Jack Parker-Holder, Yilun Du, Jake Bruce, Andre Barreto, Pieter Abbeel, Dale Schuurmans

Viaarxiv icon

Temporal Abstraction in Reinforcement Learning with the Successor Representation

Oct 12, 2021
Marlos C. Machado, Andre Barreto, Doina Precup

Figure 1 for Temporal Abstraction in Reinforcement Learning with the Successor Representation
Figure 2 for Temporal Abstraction in Reinforcement Learning with the Successor Representation
Figure 3 for Temporal Abstraction in Reinforcement Learning with the Successor Representation
Figure 4 for Temporal Abstraction in Reinforcement Learning with the Successor Representation
Viaarxiv icon

Discovering Diverse Nearly Optimal Policies withSuccessor Features

Jun 01, 2021
Tom Zahavy, Brendan O'Donoghue, Andre Barreto, Volodymyr Mnih, Sebastian Flennerhag, Satinder Singh

Figure 1 for Discovering Diverse Nearly Optimal Policies withSuccessor Features
Figure 2 for Discovering Diverse Nearly Optimal Policies withSuccessor Features
Figure 3 for Discovering Diverse Nearly Optimal Policies withSuccessor Features
Figure 4 for Discovering Diverse Nearly Optimal Policies withSuccessor Features
Viaarxiv icon

Coverage as a Principle for Discovering Transferable Behavior in Reinforcement Learning

Feb 24, 2021
Víctor Campos, Pablo Sprechmann, Steven Hansen, Andre Barreto, Steven Kapturowski, Alex Vitvitskyi, Adrià Puigdomènech Badia, Charles Blundell

Figure 1 for Coverage as a Principle for Discovering Transferable Behavior in Reinforcement Learning
Figure 2 for Coverage as a Principle for Discovering Transferable Behavior in Reinforcement Learning
Figure 3 for Coverage as a Principle for Discovering Transferable Behavior in Reinforcement Learning
Figure 4 for Coverage as a Principle for Discovering Transferable Behavior in Reinforcement Learning
Viaarxiv icon

Discovering a set of policies for the worst case reward

Feb 08, 2021
Tom Zahavy, Andre Barreto, Daniel J Mankowitz, Shaobo Hou, Brendan O'Donoghue, Iurii Kemaev, Satinder Baveja Singh

Figure 1 for Discovering a set of policies for the worst case reward
Figure 2 for Discovering a set of policies for the worst case reward
Figure 3 for Discovering a set of policies for the worst case reward
Figure 4 for Discovering a set of policies for the worst case reward
Viaarxiv icon

Temporal Difference Uncertainties as a Signal for Exploration

Oct 05, 2020
Sebastian Flennerhag, Jane X. Wang, Pablo Sprechmann, Francesco Visin, Alexandre Galashov, Steven Kapturowski, Diana L. Borsa, Nicolas Heess, Andre Barreto, Razvan Pascanu

Figure 1 for Temporal Difference Uncertainties as a Signal for Exploration
Figure 2 for Temporal Difference Uncertainties as a Signal for Exploration
Figure 3 for Temporal Difference Uncertainties as a Signal for Exploration
Figure 4 for Temporal Difference Uncertainties as a Signal for Exploration
Viaarxiv icon

Disentangled Cumulants Help Successor Representations Transfer to New Tasks

Nov 25, 2019
Christopher Grimm, Irina Higgins, Andre Barreto, Denis Teplyashin, Markus Wulfmeier, Tim Hertweck, Raia Hadsell, Satinder Singh

Figure 1 for Disentangled Cumulants Help Successor Representations Transfer to New Tasks
Figure 2 for Disentangled Cumulants Help Successor Representations Transfer to New Tasks
Figure 3 for Disentangled Cumulants Help Successor Representations Transfer to New Tasks
Figure 4 for Disentangled Cumulants Help Successor Representations Transfer to New Tasks
Viaarxiv icon

General non-linear Bellman equations

Jul 08, 2019
Hado van Hasselt, John Quan, Matteo Hessel, Zhongwen Xu, Diana Borsa, Andre Barreto

Figure 1 for General non-linear Bellman equations
Figure 2 for General non-linear Bellman equations
Viaarxiv icon

Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates

Jun 19, 2019
Hugo Penedones, Carlos Riquelme, Damien Vincent, Hartmut Maennel, Timothy Mann, Andre Barreto, Sylvain Gelly, Gergely Neu

Figure 1 for Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates
Figure 2 for Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates
Figure 3 for Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates
Figure 4 for Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates
Viaarxiv icon

Fast Task Inference with Variational Intrinsic Successor Features

Jun 12, 2019
Steven Hansen, Will Dabney, Andre Barreto, Tom Van de Wiele, David Warde-Farley, Volodymyr Mnih

Figure 1 for Fast Task Inference with Variational Intrinsic Successor Features
Figure 2 for Fast Task Inference with Variational Intrinsic Successor Features
Figure 3 for Fast Task Inference with Variational Intrinsic Successor Features
Figure 4 for Fast Task Inference with Variational Intrinsic Successor Features
Viaarxiv icon