Matteo Hessel
Artificial Intelligence · 2015–2025
A researcher in the Science corpus: 21 papers; trusts 676 researchers and is trusted by 1,138 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 576 citations into it; #963 of 36,961 by trust here, #1,102 by citations
- Reinforcement Learning — 462 citations into it; #158 of 2,250 by trust here, #93 by citations
- Management Science and Operations Research — 139 citations into it; #3,122 of 12,201 by trust here, #665 by citations
- Control and Systems Engineering — 97 citations into it; #4,603 of 8,519 by trust here, #3,599 by citations
- Optimization & Training — 93 citations into it; #2,341 of 2,605 by trust here, #1,180 by citations
- Computer Vision and Pattern Recognition — 90 citations into it
- Cognitive Neuroscience — 57 citations into it; #4,289 of 11,026 by trust here, #1,899 by citations
- Computational Theory and Mathematics — 51 citations into it; #12,382 of 12,489 by trust here, #5,245 by citations
Whom Matteo Hessel trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Richard S. Sutton
- Hado van Hasselt
- David Silver
- Volodymyr Mnih
- Marc G. Bellemare
- Yoshua Bengio
- Ronald J. Williams
- Geoffrey E. Hinton
- Diederik P. Kingma
- J. Urgen Schmidhuber
Who trusts Matteo Hessel overall
- Hado van Hasselt
- Danijar Hafner
- Pieter Abbeel
- Sergey Levine
- Yoshua Bengio
- Adam Stooke
- Pablo Samuel Castro
- Zhongwen Xu
- Yuxi Li
- Shansi Zhang
Papers from Matteo Hessel's perspective
Ordered by how strongly the researchers Matteo Hessel trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Dueling Network Architectures for Deep Reinforcement Learning (2015) — 4,476 citations
- Rainbow: Combining Improvements in Deep Reinforcement Learning (2017) — 2,665 citations
- Distributed Prioritized Experience Replay (2018) — 833 citations
- The Predictron: End-To-End Learning and Planning (2016) — 310 citations
- Multi-task Deep Reinforcement Learning with PopArt (2018) — 363 citations
- Observe and Look Further: Achieving Consistent Performance on Atari (2018) — 127 citations
- Deep Reinforcement Learning and the Deadly Triad (2018) — 287 citations
- When to use parametric models in reinforcement learning? (2019) — 211 citations
- Behaviour Suite for Reinforcement Learning (2019) — 212 citations
- Learning values across many orders of magnitude (2016) — 205 citations
- Off-Policy Actor-Critic with Shared Experience Replay (2019) — 71 citations
- Learning functions across many orders of magnitudes (2016) — 17 citations
- Unicorn: Continual Learning with a Universal, Off-policy Agent (2018) — 48 citations
- Discovering Reinforcement Learning Algorithms (2020) — 149 citations
- Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement (2018) — 192 citations
- Discovery of Useful Questions as Auxiliary Tasks (2019) — 90 citations
- Meta-Gradient Reinforcement Learning with an Objective Discovered Online (2020) — 90 citations
- Self-Tuning Deep Reinforcement Learning (2020) — 15 citations
- On Inductive Biases in Deep Reinforcement Learning (2019) — 47 citations
- What Can Learned Intrinsic Rewards Capture? (2019) — 88 citations