Sotabase

Career

· PhD in Electrical Engineering and Computer Science, Massachusetts Institute of Technology (MIT)1998–
· Professor, Stanford University1998–
· SM in Electrical Engineering and Computer Science, Massachusetts Institute of Technology (MIT)1995–
· SB in Computer Science and Engineering, Massachusetts Institute of Technology (MIT)1993–
· Co-founder and Research Programs Lead, Enuvis (acquired by SiRF/Qualcomm)
· Co-founder, Enuvis, Inc.
· Founder and Leader, Efficient Agent Team, Google DeepMind
· Research Programs Lead, Morgan Stanley
· Research Programs Lead, Unica (acquired by IBM)

Publications (410)

An Analysis of Temporal-Difference Learning with Function Approximation
1998
1,568
cited
Deep Exploration via Bootstrapped DQN
Neural Information Processing Systems · 2016
1,444
cited
A Tutorial on Thompson Sampling
Found. Trends Mach. Learn. · 2017
1,103
cited
The Linear Programming Approach to Approximate Dynamic Programming
Operational Research · 2003
802
cited
Learning to Optimize via Posterior Sampling
Mathematics of Operations Research · 2013
742
cited
Regression methods for pricing complex American-style options
IEEE Trans. Neural Networks · 2001
686
cited
Feature-based methods for large scale dynamic programming
Proceedings of 1995 34th IEEE Conference on Decision and Control · 1995
611
cited
(More) Efficient Reinforcement Learning via Posterior Sampling
Neural Information Processing Systems · 2013
571
cited
An Information-Theoretic Analysis of Thompson Sampling
Journal of machine learning research · 2014
449
cited
On Constraint Sampling in the Linear Programming Approach to Approximate Dynamic Programming
Mathematics of Operations Research · 2004
434
cited
Optimal stopping of Markov processes: Hilbert space theory, approximation algorithms, and an application to pricing high-dimensional financial derivatives
IEEE Transactions on Automatic Control · 1999
373
cited
Generalization and Exploration via Randomized Value Functions
International Conference on Machine Learning · 2014
331
cited
Deep Exploration via Randomized Value Functions
Journal of machine learning research · 2017
322
cited
Learning to Optimize via Information-Directed Sampling
Neural Information Processing Systems · 2014
306
cited
Why is Posterior Sampling Better than Optimism for Reinforcement Learning?
International Conference on Machine Learning · 2016
277
cited
Consensus Propagation
IEEE Transactions on Information Theory · 2005
268
cited
Eluder Dimension and the Sample Complexity of Optimistic Exploration
Neural Information Processing Systems · 2013
263
cited
Dynamic Pricing with a Prior on Market Response
Operational Research · 2010
218
cited
Behaviour Suite for Reinforcement Learning
International Conference on Learning Representations · 2019
201
cited
Model-based Reinforcement Learning and the Eluder Dimension
Neural Information Processing Systems · 2014
198
cited
Sotabase
Benjamin Van Roy | Researcher Profile | Sotabase | Sotabase