General Uncertainty Estimation with Delta Variances

Authors: Schmitt, Simon, Shawe-Taylor, John, van Hasselt, Hado

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Applications, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2502.14698

Normalization and effective learning rates in reinforcement learning

Authors: Lyle, Clare, Zheng, Zeyu, Khetarpal, Khimya, Martens, James, van Hasselt, Hado, Pascanu, Razvan, Dabney, Will

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2407.01800

Disentangling the Causes of Plasticity Loss in Neural Networks

Authors: Lyle, Clare, Zheng, Zeyu, Khetarpal, Khimya, van Hasselt, Hado, Pascanu, Razvan, Martens, James, Dabney, Will

Subject Terms: Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2402.18762

A Survey of Temporal Credit Assignment in Deep Reinforcement Learning

Authors: Pignatelli, Eduardo, Ferret, Johan, Geist, Matthieu, Mesnard, Thomas, van Hasselt, Hado, Pietquin, Olivier, Toni, Laura

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2312.01072

A Definition of Continual Reinforcement Learning

Authors: Abel, David, Barreto, André, Van Roy, Benjamin, Precup, Doina, van Hasselt, Hado, Singh, Satinder

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2307.11046

On the Convergence of Bounded Agents

Authors: Abel, David, Barreto, André, van Hasselt, Hado, Van Roy, Benjamin, Precup, Doina, Singh, Satinder

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2307.11044

Exploration via Epistemic Value Estimation

Authors: Schmitt, Simon, Shawe-Taylor, John, van Hasselt, Hado

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2303.04012

Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration

Authors: Jiang, Chentian, Ke, Nan Rosemary, van Hasselt, Hado

Subject Terms: Computer Science - Machine Learning, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2302.04250

Optimistic Meta-Gradients

Authors: Flennerhag, Sebastian, Zahavy, Tom, O'Donoghue, Brendan, van Hasselt, Hado, György, András, Singh, Satinder

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Mathematics - Optimization and Control

Access URL: http://arxiv.org/abs/2301.03236

Human-level Atari 200x faster

Authors: Kapturowski, Steven, Campos, Víctor, Jiang, Ray, Rakićević, Nemanja, van Hasselt, Hado, Blundell, Charles, Badia, Adrià Puigdomènech

Subject Terms: Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2209.07550

Selective Credit Assignment

Authors: Chelu, Veronica, Borsa, Diana, Precup, Doina, van Hasselt, Hado

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2202.09699

Chaining Value Functions for Off-Policy Learning

Authors: Schmitt, Simon, Shawe-Taylor, John, van Hasselt, Hado

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2201.06468

Self-Consistent Models and Values

Authors: Farquhar, Gregory, Baumli, Kate, Marinho, Zita, Filos, Angelos, Hessel, Matteo, van Hasselt, Hado, Silver, David

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2110.12840

Pick Your Battles: Interaction Graphs as Population-Level Objectives for Strategic Diversity

Authors: Garnelo, Marta, Czarnecki, Wojciech Marian, Liu, Siqi, Tirumala, Dhruva, Oh, Junhyuk, Gidel, Gauthier, van Hasselt, Hado, Balduzzi, David

Subject Terms: Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2110.04041

Introducing Symmetries to Black Box Meta Reinforcement Learning

Authors: Kirsch, Louis, Flennerhag, Sebastian, van Hasselt, Hado, Friesen, Abram, Oh, Junhyuk, Chen, Yutian

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Neural and Evolutionary Computing, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2109.10781

Bootstrapped Meta-Learning

Authors: Flennerhag, Sebastian, Schroecker, Yannick, Zahavy, Tom, van Hasselt, Hado, Silver, David, Singh, Satinder

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2109.04504

Learning Expected Emphatic Traces for Deep RL

Authors: Jiang, Ray, Zhang, Shangtong, Chelu, Veronica, White, Adam, van Hasselt, Hado

Subject Terms: Computer Science - Machine Learning, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2107.05405

Emphatic Algorithms for Deep Reinforcement Learning

Authors: Jiang, Ray, Zahavy, Tom, Xu, Zhongwen, White, Adam, Hessel, Matteo, Blundell, Charles, van Hasselt, Hado

Source: Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021

Subject Terms: Computer Science - Machine Learning, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2106.11779

Podracer architectures for scalable Reinforcement Learning

Authors: Hessel, Matteo, Kroiss, Manuel, Clark, Aidan, Kemaev, Iurii, Quan, John, Keck, Thomas, Viola, Fabio, van Hasselt, Hado

Subject Terms: Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2104.06272

Muesli: Combining Improvements in Policy Optimization

Authors: Hessel, Matteo, Danihelka, Ivo, Viola, Fabio, Guez, Arthur, Schmitt, Simon, Sifre, Laurent, Weber, Theophane, Silver, David, van Hasselt, Hado

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2104.06159