André Barreto 0001
36 publications
9 venues
H Index 14
Affiliation
Google DeepMindNational Laboratory for Scientific Computing (LNCC)
Federal University of Rio de Janeiro, Brazil
Links
| Name | Venue | Year | citations |
|---|---|---|---|
Optimizing Return Distributions with Distributional Dynamic Programming.
|
JMLR | 2025 | 6 |
| A Distributional Analogue to the Successor Representation.
|
ICML | 2024 | 11 |
| Position: Video as the New Language for Real-World Decision Making.
|
ICML | 2024 | 0 |
| Deep Reinforcement Learning with Plasticity Injection.
|
NIPS/NeurIPS | 2023 | 66 |
| A Definition of Continual Reinforcement Learning.
|
NIPS/NeurIPS | 2023 | 118 |
| Temporal Abstraction in Reinforcement Learning with the Successor Representation.
|
JMLR | 2023 | 0 |
| The Phenomenon of Policy Churn.
|
NIPS/NeurIPS | 2022 | 33 |
| Approximate Value Equivalence.
|
NIPS/NeurIPS | 2022 | 6 |
| Generalised Policy Improvement with Geometric Policy Composition.
|
ICML | 2022 | 11 |
| Model-Value Inconsistency as a Signal for Epistemic Uncertainty.
|
ICML | 2022 | 0 |
| Risk-Aware Transfer in Reinforcement Learning using Successor Features.
|
NIPS/NeurIPS | 2021 | 0 |
| Proper Value Equivalence.
|
NIPS/NeurIPS | 2021 | 40 |
| Discovering a set of policies for the worst case reward.
|
ICLR | 2021 | 25 |
| The Value-Improvement Path: Towards Better Representations for Reinforcement Learning.
|
AAAI | 2021 | 0 |
| Expected Eligibility Traces.
|
AAAI | 2021 | 0 |
| Temporally-Extended ε-Greedy Exploration.
|
ICLR | 2021 | 0 |
| On Efficiency in Hierarchical Reinforcement Learning.
|
NIPS/NeurIPS | 2020 | 41 |
| The Value Equivalence Principle for Model-Based Reinforcement Learning.
|
NIPS/NeurIPS | 2020 | 91 |
| Fast Task Inference with Variational Intrinsic Successor Features.
|
ICLR | 2020 | 0 |
| Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates.
|
NIPS/NeurIPS | 2019 | 10 |
| Composing Entropic Policies using Divergence Correction.
|
ICML | 2019 | 0 |
| The Option Keyboard: Combining Skills in Reinforcement Learning.
|
NIPS/NeurIPS | 2019 | 0 |
| Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement.
|
ICML | 2018 | 179 |
| Fast deep reinforcement learning using online adjustments from the past.
|
NIPS/NeurIPS | 2018 | 45 |
| Value-Aware Loss Function for Model-based Reinforcement Learning.
|
AISTATS | 2017 | 122 |
| Natural Value Approximators: Learning when to Trust Past Estimates.
|
NIPS/NeurIPS | 2017 | 9 |
| The Predictron: End-To-End Learning and Planning.
|
ICML | 2017 | 0 |
| Successor Features for Transfer in Reinforcement Learning.
|
NIPS/NeurIPS | 2017 | 0 |
| Incremental Stochastic Factorization for Online Reinforcement Learning.
|
AAAI | 2016 | 9 |
| Practical Kernel-Based Reinforcement Learning.
|
JMLR | 2016 | 0 |
| An Expectation-Maximization Algorithm to Compute a Stochastic Factorization From Data.
|
IJCAI | 2015 | 2 |
| Tree-Based On-Line Reinforcement Learning.
|
AAAI | 2014 | 5 |
| Policy Iteration Based on Stochastic Factorization.
|
JAIR | 2014 | 16 |
| On-line Reinforcement Learning Using Incremental Kernel-Based Stochastic Factorization.
|
NIPS/NeurIPS | 2012 | 21 |
| Reinforcement Learning using Kernel-Based Stochastic Factorization.
|
NIPS/NeurIPS | 2011 | 43 |
| Restricted gradient-descent algorithm for value-function approximation in reinforcement learning.
|
Artificial Intelligence | 2008 | 59 |