World's Best Scientists 2026 revealed!

D-Index & Metrics

Engineering and Technology

D-Index
60
Citations
15956
World Ranking
2144
National Ranking
679

Research.com Recognitions

  • 1992 - EURO Gold Medal

Overview

Benjamin Van Roy is affiliated with Stanford University in the United States. Their research focuses primarily on computer science, with a significant emphasis on artificial intelligence and management science and operations research. The subfields of their work also include electrical and electronic engineering, information systems, and computer science applications.

The scientist's main research topics include advanced bandit algorithms, reinforcement learning in robotics, machine learning and algorithms, data stream mining techniques, explainable artificial intelligence (XAI), Gaussian processes and Bayesian inference, and evolutionary algorithms and applications.

Benjamin Van Roy has a substantial publication record in several venues. Notable publication venues where their work appears include:

  • arXiv (Cornell University)
  • Foundations and Trends® in Machine Learning
  • Mathematics of Operations Research
  • Open Mind
  • Auerbach Publications eBooks

Recent papers by Benjamin Van Roy include:

  • "Satisficing in Time-Sensitive Bandit Learning," 2022, Mathematics of Operations Research
  • "Hypermodels for Exploration," 2020, arXiv (Cornell University)
  • "Reinforcement Learning, Bit by Bit," 2023, Foundations and Trends® in Machine Learning
  • "A Definition of Continual Reinforcement Learning," 2023, arXiv (Cornell University)
  • "Non-Stationary Bandit Learning via Predictive Sampling," 2022, arXiv (Cornell University)

Among frequent co-authors with whom Benjamin Van Roy has collaborated repeatedly are Vikranth Dwaracherla, Ian Osband, Dilip Arumugam, Wen Zheng, and Morteza Ibrahimi.

Benjamin Van Roy was awarded the EURO Gold Medal in 1992.

Best Publications

  • Analysis of Temporal-Diffference Learning with Function Approximation

    John N. Tsitsiklis;Benjamin Van Roy

  • Deep exploration via bootstrapped DQN

    Ian Osband;Charles Blundell;Alexander Pritzel;Benjamin Van Roy

  • Regression methods for pricing complex American-style options

    J.N. Tsitsiklis;B. Van Roy

  • Feature-based methods for large scale dynamic programming

    John N. Tsitsiklis;Benjamin van Roy

  • A Tutorial on Thompson Sampling

    Daniel J. Russo;Benjamin Van Roy;Abbas Kazerouni;Ian Osband

  • Learning to Optimize via Posterior Sampling

    Daniel Russo;Benjamin Van Roy

  • Markov Perfect Industry Dynamics with Many Firms

    Gabriel Y. Weintraub;C. Lanier Benkard;Benjamin Van Roy

  • On Constraint Sampling in the Linear Programming Approach to Approximate Dynamic Programming

    Daniela Pucci de Farias;Benjamin Van Roy

  • Optimal stopping of Markov processes: Hilbert space theory, approximation algorithms, and an application to pricing high-dimensional financial derivatives

    J.N. Tsitsiklis;B. van Roy

  • An information-theoretic analysis of Thompson sampling

    Daniel Russo;Benjamin Van Roy

  • More) Efficient Reinforcement Learning via Posterior Sampling

    Ian Osband;Dan Russo;Benjamin Van Roy

  • Dynamic Pricing with a Prior on Market Response

    Vivek F. Farias;Benjamin Van Roy

  • Consensus Propagation

    Unknown

  • Solving Data Mining Problems Through Pattern Recognition

    Christopher D. Reed;Yuchun Lee;Benjamin Van Roy

  • Generalization and exploration via randomized value functions

    Ian Osband;Benjamin Van Roy;Zheng Wen

  • A neuro-dynamic programming approach to retailer inventory management

    B. Van Roy;D.P. Bertsekas;Y. Lee;J.N. Tsitsiklis

  • Deep Exploration via Randomized Value Functions

    Ian Osband;Benjamin Van Roy;Daniel J. Russo;Zheng Wen

  • A Nonparametric Approach to Multiproduct Pricing

    Paat Rusmevichientong;Benjamin Van Roy;Peter W. Glynn

  • Brief paper: Average cost temporal-difference learning

    John N. Tsitsiklis;Benjamin Van Roy

  • Why is posterior sampling better than optimism for reinforcement learning

    Ian Osband;Benjamin Van Roy

  • Eluder Dimension and the Sample Complexity of Optimistic Exploration

    Dan Russo;Benjamin Van Roy

  • Feature-based methods for large scale dynamic programming

    J.N. Tsitsiklis;B. Van Roy

Frequent Co-Authors

Richard J. Zeckhauser
Richard J. Zeckhauser Harvard University
Anant Sahai
Anant Sahai University of California, Berkeley
Tsachy Weissman
Tsachy Weissman Stanford University
Satinder Singh
Satinder Singh DeepMind (United Kingdom)
Mohammad Ghavamzadeh
Mohammad Ghavamzadeh Amazon (United States)
Peter W. Glynn
Peter W. Glynn Stanford University
David Silver
David Silver DeepMind (United Kingdom)
Charles Blundell
Charles Blundell DeepMind (United Kingdom)
Ramesh Johari
Ramesh Johari Stanford University
Tengyu Ma
Tengyu Ma Stanford University

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Best Scientists Citing Benjamin Van Roy

Trending Scientists