Mohammad Gheshlaghi Azar
Artificial Intelligence · 2010–2023
A researcher in the Science corpus: 20 papers; trusts 759 researchers and is trusted by 959 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 546 citations into it; #1,091 of 36,961 by trust here, #1,024 by citations
- Reinforcement Learning — 326 citations into it; #179 of 2,250 by trust here, #154 by citations
- Computer Vision and Pattern Recognition — 158 citations into it; #3,290 of 21,973 by trust here, #2,169 by citations
- Management Science and Operations Research — 144 citations into it; #387 of 12,201 by trust here, #243 by citations
- Representation & Self-Supervised Learning — 109 citations into it
- Control and Systems Engineering — 81 citations into it; #3,794 of 8,519 by trust here, #7,018 by citations
- Optimization & Training — 69 citations into it
- Computational Theory and Mathematics — 50 citations into it
Whom Mohammad Gheshlaghi Azar trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Richard S. Sutton
- Dimitri P. Bertsekas
- R´emi Munos
- Geoffrey E. Hinton
- Diederik P. Kingma
- Andrew Barto
- Csaba Szepesvari
- Yoshua Bengio
- Sham M. Kakade
- Alex Krizhevsky
Who trusts Mohammad Gheshlaghi Azar overall
- Chi Jin
- Ofir Nachum
- Mengdi Wang
- Alekh Agarwal
- Sham M. Kakade
- Brendan O'Donoghue
- Mohammad Norouzi
- Roy Fox
- Lin F. Yang
- R´emi Munos
Papers from Mohammad Gheshlaghi Azar's perspective
Ordered by how strongly the researchers Mohammad Gheshlaghi Azar 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)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning (2020) — 8,797 citations
- Rainbow: Combining Improvements in Deep Reinforcement Learning (2017) — 2,665 citations
- Noisy Networks for Exploration (2017) — 1,022 citations
- Observe and Look Further: Achieving Consistent Performance on Atari (2018) — 127 citations
- Minimax Regret Bounds for Reinforcement Learning (2017) — 882 citations
- The Reactor: A Sample-Efficient Actor-Critic Architecture (2017) — 59 citations
- The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning (2017) — 103 citations
- Neural Predictive Belief Representations (2018) — 82 citations
- Hindsight Credit Assignment (2019) — 95 citations
- Dynamic policy programming (2010) — 138 citations
- On the Sample Complexity of Reinforcement Learning with a Generative Model (2012) — 158 citations
- Speedy Q-Learning (2011) — 212 citations
- World Discovery Models (2019) — 28 citations
- Dynamic Policy Programming with Function Approximation (2011) — 39 citations
- Meta-learning of Sequential Strategies (2019) — 120 citations
- A General Theoretical Paradigm to Understand Learning from Human Preferences (2023) — 1,063 citations
- Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning (2020) — 158 citations
- Sequential Transfer in Multi-armed Bandit with Finite Set of Models (2013) — 118 citations
- Large-Scale Representation Learning on Graphs via Bootstrapping (2021) — 329 citations
- Bootstrapped Representation Learning on Graphs (2021) — 315 citations