Folgen
Matteo Hessel
Matteo Hessel
Research Engineer, Google DeepMind
Bestätigte E-Mail-Adresse bei google.com
Titel
Zitiert von
Zitiert von
Jahr
Dueling Network Architectures for Deep Reinforcement Learning
Z Wang, T Schaul, M Hessel, H Van Hasselt, M Lanctot, N De Freitas
International Conference on Machine Learning (ICML 2016), 1995–2003, 2016
49172016
Rainbow: Combining Improvements in Deep Reinforcement Learning
M Hessel, J Modayil, H van Hasselt, T Schaul, G Ostrovski, W Dabney, ...
Association for the Advancement of Artificial Intelligence (AAAI 2018), 2017
25882017
Distributed Prioritized Experience Replay
D Horgan, J Quan, D Budden, G Barth-Maron, M Hessel, H van Hasselt, ...
International Conference on Learning Representations (ICLR 2018), 2018
8582018
The predictron: End-to-end learning and planning
D Silver, H van Hasselt, M Hessel, T Schaul, A Guez, T Harley, ...
International Conference on Machine Learning (ICML 2017), 3191--3199, 2016
3002016
Multi-task Deep Reinforcement Learning with PopArt
M Hessel, H Soyer, L Espeholt, W Czarnecki, S Schmitt, H van Hasselt
Association for the Advancement of Artificial Intelligence (AAAI 2019), 2018
2982018
Deep Reinforcement Learning and the Deadly Triad
H van Hasselt, Y Doron, F Strub, M Hessel, N Sonnerat, J Modayil
Deep Reinforcement Learning Workshop (NeurIPS 2018), 2018
2482018
When to use parametric models in reinforcement learning?
HP van Hasselt, M Hessel, J Aslanides
Advances in Neural Information Processing Systems (NeurIPS 2019), 2019
2062019
Learning values across many orders of magnitude
HP van Hasselt, A Guez, M Hessel, V Mnih, D Silver
Advances In Neural Information Processing Systems (NIPS 2016), 4287-4295, 2016
1872016
Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement
A Barreto, D Borsa, J Quan, T Schaul, D Silver, M Hessel, D Mankowitz, ...
International Conference on Machine Learning (ICML 2018), 510-519, 2018
1852018
Behaviour Suite for Reinforcement Learning
I Osband, Y Doron, M Hessel, J Aslanides, E Sezener, A Saraiva, ...
International Conference on Learning Representations (ICLR 2020), 2019
1782019
Discovering reinforcement learning algorithms
J Oh, M Hessel, WM Czarnecki, Z Xu, HP van Hasselt, S Singh, D Silver
Advances in Neural Information Processing Systems 33, 1060-1070, 2020
1432020
Observe and Look Further: Achieving Consistent Performance on Atari
T Pohlen, B Piot, T Hester, MG Azar, D Horgan, D Budden, G Barth-Maron, ...
arXiv preprint arXiv:1805.11593, 2018
1362018
The DeepMind JAX Ecosystem, 2020
I Babuschkin, K Baumli, A Bell, S Bhupatiraju, J Bruce, P Buchlovsky, ...
URL http://github. com/deepmind 5, 2010
962010
Discovery of useful questions as auxiliary tasks
V Veeriah, M Hessel, Z Xu, J Rajendran, RL Lewis, J Oh, HP van Hasselt, ...
Advances in Neural Information Processing Systems (NeurIPS 2019), 9310-9321, 2019
942019
What Can Learned Intrinsic Rewards Capture?
Z Zheng, J Oh, M Hessel, Z Xu, M Kroiss, H van Hasselt, D Silver, S Singh
International Conference on Machine Learning (ICML 2020), 0
91*
A self-tuning actor-critic algorithm
T Zahavy, Z Xu, V Veeriah, M Hessel, J Oh, HP van Hasselt, D Silver, ...
Advances in neural information processing systems 33, 20913-20924, 2020
852020
Meta-gradient reinforcement learning with an objective discovered online
Z Xu, HP van Hasselt, M Hessel, J Oh, S Singh, D Silver
Advances in Neural Information Processing Systems 33, 15254-15264, 2020
792020
Muesli: Combining improvements in policy optimization
M Hessel, I Danihelka, F Viola, A Guez, S Schmitt, L Sifre, T Weber, ...
International Conference on Machine Learning, 4214-4226, 2021
762021
Off-Policy Actor-Critic with Shared Experience Replay
S Schmitt, M Hessel, K Simonyan
International Conference on Machine Learning (ICML 2020), 2019
522019
Optax: composable gradient transformation and optimisation
M Hessel, D Budden, F Viola, M Rosca, E Sezener, T Hennigan
JAX, http://github. com/deepmind/optax (last access: 4 July 2023), version 0.0 1, 2020
492020
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20