Benjamin Van Roy
Artificial Intelligence · 1995–2020
A researcher in the Science corpus: 31 papers; trusts 394 researchers and is trusted by 1,725 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 348 citations into it; #729 of 36,961 by trust here, #1,521 by citations
- Reinforcement Learning — 273 citations into it; #62 of 2,250 by trust here, #114 by citations
- Management Science and Operations Research — 240 citations into it; #66 of 12,201 by trust here, #79 by citations
- Statistical Learning Theory — 55 citations into it; #725 of 1,040 by trust here, #541 by citations
- Statistics and Probability — 54 citations into it
- Control and Systems Engineering — 50 citations into it; #984 of 8,519 by trust here, #1,417 by citations
- Computer Networks and Communications — 46 citations into it; #297 of 9,996 by trust here, #677 by citations
- Probabilistic & Bayesian Methods — 40 citations into it; #545 of 1,526 by trust here, #601 by citations
Whom Benjamin Van Roy trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Ian Osband
- Richard S. Sutton
- Daniel Russo
- Dimitri P. Bertsekas
- Malcolm J. A. Strens
- Michael Kearns
- Peter Auer
- Sham M. Kakade
- Satinder Singh
- Csaba Szepesvari
Who trusts Benjamin Van Roy overall
- Ian Osband
- Brendan O'Donoghue
- Richard S. Sutton
- Sergey Levine
- Huizhen Yu
- Daniel Russo
- Yuxi Li
- Csaba Szepesvari
- Dimitri P. Bertsekas
- Lihong Li
Papers from Benjamin Van Roy's perspective
Ordered by how strongly the researchers Benjamin Van Roy 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)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Reinforcement Learning: An Introduction
- Attention is All you Need (Neural Information Processing Systems)
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- Deep Exploration via Bootstrapped DQN (2016) — 1,541 citations
- (More) Efficient Reinforcement Learning via Posterior Sampling (2013) — 595 citations
- Generalization and Exploration via Randomized Value Functions (2014) — 339 citations
- Deep Exploration via Randomized Value Functions (2017) — 339 citations
- Behaviour Suite for Reinforcement Learning (2019) — 212 citations
- A Tutorial on Thompson Sampling (2017) — 1,218 citations
- Why is Posterior Sampling Better than Optimism for Reinforcement Learning? (2016) — 289 citations
- An analysis of temporal-difference learning with function approximation (1997)
- Learning to Optimize via Posterior Sampling (2013) — 780 citations
- Learning to Optimize via Information-Directed Sampling (2014) — 336 citations
- On Constraint Sampling in the Linear Programming Approach to Approximate Dynamic Programming (2004) — 434 citations
- Model-based Reinforcement Learning and the Eluder Dimension (2014) — 206 citations
- Near-optimal Reinforcement Learning in Factored MDPs (2014) — 138 citations
- On Lower Bounds for Regret in Reinforcement Learning (2016) — 109 citations
- Bootstrapped Thompson Sampling and Deep Exploration (2015) — 114 citations
- An Information-Theoretic Analysis of Thompson Sampling (2014) — 466 citations
- Time-Sensitive Bandit Learning and Satisficing Thompson Sampling (2017) — 12 citations
- The Linear Programming Approach to Approximate Dynamic Programming (2003) — 812 citations
- Regression methods for pricing complex American-style options (2001) — 676 citations
- Coordinated Exploration in Concurrent Reinforcement Learning (2018) — 46 citations