Romain Laroche

Artificial Intelligence · 2010–2022

A researcher in the Science corpus: 14 papers; trusts 205 researchers and is trusted by 53 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 197 citations into it; #9,724 of 35,345 by trust here, #8,157 by citations
• Reinforcement Learning — 185 citations into it; #404 of 2,242 by trust here, #648 by citations
• Natural Language Processing — 44 citations into it
• Management Science and Operations Research — 43 citations into it; #10,569 of 11,946 by trust here, #11,360 by citations
• Computer Vision and Pattern Recognition — 32 citations into it
• Control and Systems Engineering — 22 citations into it
• Computational Theory and Mathematics — 17 citations into it
• Optimization & Training — 14 citations into it

Whom Romain Laroche trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Richard S. Sutton
2. Peter Auer
3. Philip S. Thomas
4. Mohammad Ghavamzadeh
5. Andrew Barto
6. Kaiming He
7. Geoffrey E. Hinton
8. Damien Ernst
9. Marc G. Bellemare
10. Volodymyr Mnih

Who trusts Romain Laroche overall

1. Thiago D. Simão
2. Aviral Kumar
3. Scott Fujimoto
4. Justin Fu
5. Sergey Levine
6. George Tucker
7. Ruosong Wang
8. Rishabh Agarwal
9. Jacob Buckman
10. Ying Jin

Papers from Romain Laroche's perspective

Ordered by how strongly the researchers Romain Laroche trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Long Short-Term Memory
5. Attention is All you Need (Neural Information Processing Systems)
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
8. Reinforcement Learning: An Introduction
9. Learning Multiple Layers of Features from Tiny Images
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Counting to Explore and Generalize in Text-based Games (2018) — 76 citations
• Hybrid Reward Architecture for Reinforcement Learning (2017) — 292 citations
• Learning Dynamic Belief Graphs to Generalize on Text-Based Games (2020) — 88 citations
• Safe Policy Improvement with an Estimated Baseline Policy (2019) — 26 citations
• Safe Policy Improvement with Soft Baseline Bootstrapping (2019) — 37 citations
• Transfer Learning for User Adaptation in Spoken Dialogue Systems (2016) — 39 citations
• Decentralized Exploration in Multi-Armed Bandits (2018) — 26 citations
• One-Shot Learning from a Demonstration with Hierarchical Latent Language (2022) — 8 citations
• Scaling up budgeted reinforcement learning (2019) — 4 citations
• Multi-batch Reinforcement Learning (2019) — 3 citations
• Transfer Reinforcement Learning with Shared Dynamics (2017) — 60 citations
• Safe Policy Improvement with Baseline Bootstrapping (2017) — 226 citations
• Score-based Inverse Reinforcement Learning (2016) — 41 citations
• Optimising a handcrafted dialogue system design (2010) — 9 citations