Benjamin Van Roy

发表

Directed Principal Component Analysis

Yi-Hao Kao, Benjamin Van Roy, Yi-Hao Kao, 2014, Oper. Res..

Deciding What to Learn: A Rate-Distortion Approach pdf

Benjamin Van Roy, Dilip Arumugam, 2021, ArXiv.

Capacity and Zero-Error Capacity of the Chemical Channel with Feedback

Haim H. Permuter, Tsachy Weissman, Paul W. Cuff, 2007, 2007 IEEE International Symposium on Information Theory.

Time-Sensitive Bandit Learning and Satisficing Thompson Sampling pdf

David Tse, Benjamin Van Roy, Daniel Russo, 2017, ArXiv.

Efficient Reinforcement Learning in Deterministic Systems with Value Function Generalization

Zheng Wen, Benjamin Van Roy, Zheng Wen, 2013, Math. Oper. Res..

An Information-Theoretic Analysis for Thompson Sampling with Many Actions

Shi Dong, Benjamin Van Roy, Shi Dong, 2018, NeurIPS.

Decision , Risk & Operations Working Papers Series Approximate and Data-Driven Dynamic Programming for Queueing Networks

Sunil Kumar, Benjamin Van Roy, Ciamac C. Moallemi, 2008 .

Intermediated Blind Portfolio Auctions

Benjamin Van Roy, Michael Padilla, Michael Padilla, 2012, Manag. Sci..

Bootstrapped Thompson Sampling and Deep Exploration pdf

Benjamin Van Roy, Ian Osband, Ian Osband, 2015, ArXiv.

Detecting colluders in pagerank: finding slow mixing states in a markov chain

Benjamin Van Roy, Kahn Mason, 2005 .

Strategic and Tactical Decision-Making Under Uncertainty

Michael I. Jordan, Claire J. Tomlin, Laurent El Ghaoui, 2006 .

Directed Time Series Regression for Control pdf

Yi-Hao Kao, Benjamin Van Roy, Yi-Hao Kao, 2012, ArXiv.

Randomized Value Functions via Posterior State-Abstraction Sampling pdf

Benjamin Van Roy, Dilip Arumugam, 2020, ArXiv.

Fixed Points of Approximate Value Iteration and Temporal-Difference Learning

Benjamin Van Roy, Daniela Pucci de Farias, D. D. Farias, 2000, ICML.

Gaussian-Dirichlet Posterior Dominance in Sequential Learning pdf

Benjamin Van Roy, Ian Osband, Ian Osband, 2017, ArXiv.

Tetris: A Study of Randomized Constraint Sampling

Benjamin Van Roy, Vivek F. Farias, V. Farias, 2006 .

Near-optimal Reinforcement Learning in Factored MDPs

Benjamin Van Roy, Ian Osband, Ian Osband, 2014, NIPS.

Ensemble Sampling

Benjamin Van Roy, Xiuyuan Lu, Xiuyuan Lu, 2017, NIPS.

Learning to Optimize via Information-Directed Sampling

Benjamin Van Roy, Daniel Russo, Daniel Russo, 2014, NIPS.

Provably Efficient Reinforcement Learning with Aggregated States pdf

Zhengyuan Zhou, Benjamin Van Roy, Shi Dong, 2019, ArXiv.

TD(0) Leads to Better Policies than Approximate Value Iteration

Benjamin Van Roy, 2005, NIPS.

Approximate Dynamic Programming via Linear Programming

Benjamin Van Roy, Daniela Pucci de Farias, D. D. Farias, 2001, NIPS.

Oblivious Equilibrium: A Mean Field Approximation for Large-Scale Dynamic Games

Benjamin Van Roy, Gabriel Y. Weintraub, C. Lanier Benkard, 2005, NIPS.

Consensus Propagation

Benjamin Van Roy, Ciamac C. Moallemi, C. Moallemi, 2005, IEEE Transactions on Information Theory.

Computational Methods for Oblivious Equilibrium

Benjamin Van Roy, Gabriel Y. Weintraub, C. Lanier Benkard, 2010, Oper. Res..

Distributed Optimization in Adaptive Networks

Benjamin Van Roy, Ciamac C. Moallemi, C. Moallemi, 2003, NIPS.

On Regression-Based Stopping Times

Benjamin Van Roy, 2010, Discret. Event Dyn. Syst..

Documentation of the Oblivious Equilibrium Solver

Benjamin Van Roy, Gabriel Y. Weintraub, C. Lanier Benkard, 2008 .

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

John N. Tsitsiklis, Benjamin Van Roy, J. Tsitsiklis, 1999, IEEE Trans. Autom. Control..

Solitaire: Man Versus Machine

Benjamin Van Roy, Persi Diaconis, Xiang Yan, 2004, NIPS.

Book reviews: Self-learning control of finite Markov chains

Benjamin Van Roy, 2003 .

Manipulation Robustness of Collaborative Filtering

Benjamin Van Roy, Xiang Yan, X. Yan, 2010, Manag. Sci..

Self-learning control of finite Markov chains: A.S. Poznyak, K. Najim, E. Gómez-Ramírez, Marcel Dekker, New York, 2000, $150, pp 298, ISBN 0-8247-9249-X

Benjamin Van Roy, 2003, Autom..

Analysis of Temporal-Diffference Learning with Function Approximation

John N. Tsitsiklis, Benjamin Van Roy, J. Tsitsiklis, 1996, NIPS.

The Linear Programming Approach to Approximate Dynamic Programming

Benjamin Van Roy, Daniela Pucci de Farias, D. D. Farias, 2003, Oper. Res..

Use of Approximate Dynamic Programming for Production Optimization

Zheng Wen, Louis J. Durlofsky, Benjamin Van Roy, 2011, ANSS 2011.

On Optimistic versus Randomized Exploration in Reinforcement Learning pdf

Benjamin Van Roy, Ian Osband, 2017, ArXiv.

Near-optimal Regret Bounds for Reinforcement Learning in Factored MDPs pdf

Benjamin Van Roy, Ian Osband, Ian Osband, 2014, ArXiv.

Learning to Price with Reference Effects pdf

Benjamin Van Roy, Abbas Kazerouni, Abbas Kazerouni, 2017, ArXiv.

Directed Regression

Yi-Hao Kao, Benjamin Van Roy, Xiang Yan, 2009, NIPS.

Average cost temporal-difference learning

John N. Tsitsiklis, Benjamin Van Roy, J. Tsitsiklis, 1997, Proceedings of the 36th IEEE Conference on Decision and Control.

Resource Allocation via Message Passing

Benjamin Van Roy, Ciamac C. Moallemi, C. Moallemi, 2011, INFORMS J. Comput..

Posterior Sampling for Reinforcement Learning Without Episodes pdf

Benjamin Van Roy, Ian Osband, 2016, ArXiv.

An Information-Theoretic Analysis of Thompson Sampling for Large Action Spaces pdf

Shi Dong, Benjamin Van Roy, 2018, NIPS 2018.

Why is Posterior Sampling Better than Optimism for Reinforcement Learning? pdf

Benjamin Van Roy, Ian Osband, Ian Osband, 2016, ICML.

Learning a factor model via regularized PCA

Yi-Hao Kao, Benjamin Van Roy, Yi-Hao Kao, 2011, Machine Learning.

Satisficing in Time-Sensitive Bandit Learning pdf

Benjamin Van Roy, Daniel Russo, Daniel Russo, 2018, Math. Oper. Res..

A Generalized Kalman Filter for Fixed Point Approximation and Efficient Temporal-Difference Learning

David Choi, Benjamin Van Roy, David Choi, 2001, Discret. Event Dyn. Syst..

Generalization and Exploration via Randomized Value Functions pdf

Benjamin Van Roy, Ian Osband, Zheng Wen, 2014, ICML.

Making Eigenvector-Based Reputation Systems Robust to Collusion

Ramesh Govindan, Ashish Goel, Hui Zhang, 2004, WAW.

Dynamic Pricing with a Prior on Market Response

Benjamin Van Roy, Vivek F. Farias, V. Farias, 2010, Oper. Res..

A universal scheme for learning

Tsachy Weissman, Benjamin Van Roy, Vivek F. Farias, 2005, Proceedings. International Symposium on Information Theory, 2005. ISIT 2005..

Adaptive Execution: Exploration and Learning of Price Impact

Benjamin Van Roy, Beomsoo Park, 2015, Oper. Res..

On the Performance of Thompson Sampling on Logistic Bandits

Tengyu Ma, Shi Dong, Benjamin Van Roy, 2019, COLT.

Langevin DQN pdf

Benjamin Van Roy, Vikranth Dwaracherla, 2020, ArXiv.

Behaviour Suite for Reinforcement Learning pdf

Tor Lattimore, Richard S. Sutton, Csaba Szepesvári, 2019, ICLR.

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

Benjamin Van Roy, Daniela Pucci de Farias, D. D. Farias, 2004, Math. Oper. Res..

On Lower Bounds for Regret in Reinforcement Learning pdf

Benjamin Van Roy, Ian Osband, Ian Osband, 2016, ArXiv.

Manipulation-resistant collaborative filtering systems

Benjamin Van Roy, Xiang Yan, X. Yan, 2009, RecSys '09.

Deep Exploration via Bootstrapped DQN

Benjamin Van Roy, Charles Blundell, Ian Osband, 2016, NIPS.

A Tractable POMDP for a Class of Sequencing Problems pdf

Benjamin Van Roy, Paat Rusmevichientong, 2001, UAI 2001.

Convergence of the Min-Sum Message Passing Algorithm for Quadratic Optimization pdf

Benjamin Van Roy, Ciamac C. Moallemi, C. Moallemi, 2006, ArXiv.

An analysis of belief propagation on the turbo decoding graph with Gaussian densities

Benjamin Van Roy, Paat Rusmevichientong, P. Rusmevichientong, 2001, IEEE Trans. Inf. Theory.

(More) Efficient Reinforcement Learning via Posterior Sampling

Benjamin Van Roy, Ian Osband, Daniel Russo, 2013, NIPS.

The linear programming approach to approximate dynamic programming: theory and application

Benjamin Van Roy, Daniela Pucci de Farias, D. D. Farias, 2002 .

Model-based Reinforcement Learning and the Eluder Dimension

Benjamin Van Roy, Ian Osband, Ian Osband, 2014, NIPS.

Eluder Dimension and the Sample Complexity of Optimistic Exploration

Benjamin Van Roy, Daniel Russo, Daniel Russo, 2013, NIPS.

Information-Theoretic Confidence Bounds for Reinforcement Learning

Benjamin Van Roy, Xiuyuan Lu, 2019, NeurIPS.

Efficient Reinforcement Learning for High Dimensional Linear Quadratic Systems

Adel Javanmard, Benjamin Van Roy, Morteza Ibrahimi, 2012, NIPS.

Convergence of Min-Sum Message-Passing for Convex Optimization

Benjamin Van Roy, Ciamac C. Moallemi, C. Moallemi, 2010, IEEE Transactions on Information Theory.

An Approximate Dynamic Programming Approach to Network Revenue Management

Benjamin Van Roy, Vivek F. Farias, V. Farias, 2006 .

Feature-Based Methods for Large Scale Dynamic Programming

John N. Tsitsiklis, Benjamin Van Roy, 2005, Machine Learning.

Conservative Contextual Linear Bandits

Benjamin Van Roy, Mohammad Ghavamzadeh, Abbas Kazerouni, 2016, NIPS.

Approximation algorithms for dynamic resource allocation

Benjamin Van Roy, Vivek F. Farias, 2006, Oper. Res. Lett..

Approximate Linear Programming for Average-Cost Dynamic Programming

Benjamin Van Roy, Daniela Pucci de Farias, D. D. Farias, 2002, NIPS.

Control of Diffusions via Linear Programming

Benjamin Van Roy, Jiarui Han, Jiarui Han, 2010 .

Capacity of the Trapdoor Channel With Feedback

Haim H. Permuter, Tsachy Weissman, Paul W. Cuff, 2006, IEEE Transactions on Information Theory.

On Average Versus Discounted Reward Temporal-Difference Learning

John N. Tsitsiklis, Benjamin Van Roy, J. Tsitsiklis, 2002, Machine Learning.

Efficient Exploration and Value Function Generalization in Deterministic Systems

Zheng Wen, Benjamin Van Roy, Zheng Wen, 2013, NIPS.

A Nonparametric Approach to Multiproduct Pricing

Peter W. Glynn, Benjamin Van Roy, Paat Rusmevichientong, 2006, Oper. Res..

Learning and value function approximation in complex decision processes

Benjamin Van Roy, 1998 .

Investment and Market Structure in Industries with Congestion

Benjamin Van Roy, Ramesh Johari, Gabriel Y. Weintraub, 2007, Oper. Res..

Solving Data Mining Problems Through Pattern Recognition

Benjamin Van Roy, Yuchun Lee, Christopher D. Reed, 1997 .

Manipulation Robustness of Collaborative Filtering Systems

Benjamin Van Roy, Xiang Yan, X. Yan, 2009, ArXiv.

Scalable Coordinated Exploration in Concurrent Reinforcement Learning

Benjamin Van Roy, Ian Osband, Maria Dimakopoulou, 2018, NeurIPS.

Performance Loss Bounds for Approximate Value Iteration with State Aggregation

Benjamin Van Roy, 2006, Math. Oper. Res..

Convergence of Min-Sum Message Passing for Quadratic Optimization

Benjamin Van Roy, Ciamac C. Moallemi, C. Moallemi, 2006, IEEE Transactions on Information Theory.

A Cost-Shaping LP for Bellman Error Minimization with Performance Guarantees

Benjamin Van Roy, Daniela Pucci de Farias, D. P. D. Farias, 2004, NIPS.

Convergence of Min-Sum Message Passing for

Benjamin Van Roy, Ciamac C. Moallemi, 2009 .

A short proof of optimality for the MIN cache replacement algorithm

Benjamin Van Roy, 2007, Inf. Process. Lett..

Neuro-Dynamic Programming: Overview and Recent Trends

Benjamin Van Roy, 2002 .

Stable LInear Approximations to Dynamic Programming for Stochastic Control Problems with Local Transitions

John N. Tsitsiklis, Benjamin Van Roy, J. Tsitsiklis, 1995, NIPS.

A Hybrid Method for Distance Metric Learning pdf

Daniel L. Rubin, Yi-Hao Kao, Benjamin Van Roy, 2012, ArXiv.

Regression methods for pricing complex American-style options

John N. Tsitsiklis, Benjamin Van Roy, J. Tsitsiklis, 2001, IEEE Trans. Neural Networks.

An Analysis of Turbo Decoding with Gaussian Densities

Benjamin Van Roy, Paat Rusmevichientong, P. Rusmevichientong, 1999, NIPS.

A Tutorial on Thompson Sampling

Benjamin Van Roy, Ian Osband, Daniel Russo, 2017, Found. Trends Mach. Learn..

Reputation markets

Benjamin Van Roy, Xiang Yan, 2008, NetEcon '08.

Coordinated Exploration in Concurrent Reinforcement Learning

Benjamin Van Roy, Maria Dimakopoulou, Maria Dimakopoulou, 2018, ICML.

Proceedings of the Seventeenth International Conference on Machine Learning (ICML 2000), Stanford University, Stanford, CA, USA, June 29 - July 2, 2000

Toby Walsh, Alan Bundy, Stefan Schaal, 2000, ICML.

Decentralized decision-making in a large team with local information

Benjamin Van Roy, Paat Rusmevichientong, 2003, Games Econ. Behav..

Approximate Solutions to Optimal Stopping Problems

John N. Tsitsiklis, Benjamin Van Roy, J. Tsitsiklis, 1996, NIPS.

Comments on the Du-Kakade-Wang-Yang Lower Bounds pdf

Benjamin Van Roy, Shi Dong, Shi Dong, 2019, ArXiv.

Universal Reinforcement Learning

Benjamin Van Roy, Tsachy Weissman, Vivek F. Farias, 2007, IEEE Transactions on Information Theory.

Hypermodels for Exploration pdf

Benjamin Van Roy, Ian Osband, Xiuyuan Lu, 2020, ICLR.

Strategic Execution in the Presence of an Uninformed Arbitrageur

Benjamin Van Roy, Beomsoo Park, Ciamac C. Moallemi, 2008, 0801.3001.

On Efficiency in Hierarchical Reinforcement Learning

Doina Precup, Satinder Singh, Benjamin Van Roy, 2020, NeurIPS.

An Information-Theoretic Analysis of Thompson Sampling pdf

Benjamin Van Roy, Daniel Russo, Daniel Russo, 2014, J. Mach. Learn. Res..

Deep Exploration via Randomized Value Functions

Zheng Wen, Benjamin Van Roy, Ian Osband, 2017, J. Mach. Learn. Res..

A Tractable POMDP for Dynamic Sequencing with Applications to Personalized Internet Content Provision

Benjamin Van Roy, Paat Rusmevichientong, P. Rusmevichientong, 2001, UAI.

A Cost-Shaping Linear Program for Average-Cost Approximate Dynamic Programming with Performance Guarantees

Benjamin Van Roy, Daniela Pucci de Farias, D. D. Farias, 2006, Math. Oper. Res..

Learning to Optimize via Posterior Sampling

Benjamin Van Roy, Daniel Russo, Daniel Russo, 2013, Math. Oper. Res..

Epistemic Neural Networks pdf

Zheng Wen, Benjamin Van Roy, Ian Osband, 2021, ArXiv.

Evaluating Probabilistic Inference in Deep Learning: Beyond Marginal Predictions pdf

Zheng Wen, Benjamin Van Roy, Ian Osband, 2021, ArXiv.

A Bit Better? Quantifying Information for Bandit Learning pdf

Kuang Xu, Benjamin Van Roy, Adithya M. Devraj, 2021, ArXiv.

Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent State pdf

Zhengyuan Zhou, Benjamin Van Roy, Shi Dong, 2021, ArXiv.

Deep Exploration for Recommendation Systems pdf

Benjamin Van Roy, Zheqing Zhu, 2021, ArXiv.

Evaluating Predictive Distributions: Does Bayesian Deep Learning Work? pdf

Seyed Mohammad Asghari, Benjamin Van Roy, Ian Osband, 2021, ArXiv.

Reinforcement Learning, Bit by Bit pdf

Zheng Wen, Benjamin Van Roy, Ian Osband, 2021, Found. Trends Mach. Learn..

Deciding What to Learn: A Rate-Distortion Approach

Benjamin Van Roy, Dilip Arumugam, Dilip Arumugam, 2021, ICML.

Feature-based methods for large scale dynamic programming

Benjamin Van Roy, J. Tsitsiklis, 1995 .

An approximate dynamic programming approach to decentralized control of stochastic systems

Benjamin Van Roy, S. Lall, R. Cogill, 2006 .

Convergence of the Min-Sum Algorithm for Convex Optimization

Benjamin Van Roy, C. Moallemi, 2007, 0705.4253.

Markov Perfect Industry Dynamics with Many Firms

Benjamin Van Roy, C. L. Benkard, G. Weintraub, 2005 .

A Non-Parametric Approach to Multi-Product Pricing

Benjamin Van Roy, P. Glynn, P. Rusmevichientong, 2003 .

The optimal harvesting of environmental bads

Benjamin Van Roy, N. Keohane, B. Van Roy, 2000, Proceedings of the 39th IEEE Conference on Decision and Control (Cat. No.00CH37187).

MARKOV PERFECT INDUSTRY DYNAMICS WITH MANY FIRMS

Benjamin Van Roy, C. L. Benkard, G. Weintraub, 2008 .

Long time series spatialized data for urban climatological studies: A case study of Paris, France

Benjamin Van Roy, V. Masson, A. Lemonsu, 2020, International Journal of Climatology.

APPROXIMATE DYNAMIC PROGRAMMING FOR OPTIMIZING OIL PRODUCTION

Benjamin Van Roy, L. Durlofsky, Zheng Wen, 2012 .

Transaction-Cost-Conscious Pairs Trading via Approximate Dynamic Programming Undergraduate

Benjamin Van Roy, X. Yan, 2005 .

Portfolio selection with qualitative input

Benjamin Van Roy, Anant Chiarawongse, S. Kiatsupaibul, 2012 .

A Message-Passing Paradigm for Resource Allocation

Benjamin Van Roy, C. Moallemi, 2008 .

Operation and Performance of an Optimized Real Time Control System for Wet Weather Pollution Control

Benjamin Van Roy, Martin Pleau, Hubert Colas, 2000 .

On Average versus Discounted Reward Temporal{diierence Learning 1

Benjamin Van Roy, J. Tsitsiklis, 1999 .

From Predictions to Decisions: The Importance of Joint Predictive Distributions

Benjamin Van Roy, Zheng Wen, Ian Osband, 2021, 2107.09224.

The Neural Testbed: Evaluating Joint Predictions

Benjamin Van Roy, Zheng Wen, Ian Osband, 2021, NeurIPS.

Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrapping

Benjamin Van Roy, Zheng Wen, Ian Osband, 2022, Trans. Mach. Learn. Res..

Robustness of Epinets against Distributional Shifts

Benjamin Van Roy, Ian Osband, Sven Gowal, 2022, ArXiv.

Effects of Mergers in Two-sided Markets: Examination of the U.S. Radio Industry

Benjamin Van Roy, Alan T. Sorensen, I. Segal, 2012 .

Merger enforcement in two-sided markets ∗

Benjamin Van Roy, Alan T. Sorensen, I. Segal, 2010 .

Non-Ohmic Characteristics of a Quantum Confined Degenerate Ensemble of Carriers in a Well of GaAs at Low Lattice Temperature

Benjamin Van Roy, D. Bhattacharya, S. Bhattacharyya, 2021 .

Average cost temporal-difference learning

Benjamin Van Roy, J. Tsitsiklis, B. Van Roy, 1997, Proceedings of the 36th IEEE Conference on Decision and Control.

Feature-based methods for large scale dynamic programming

Benjamin Van Roy, J. Tsitsiklis, B. Van Roy, 1995, Proceedings of 1995 34th IEEE Conference on Decision and Control.

The Tuskegee syphilis experiment: medical ethics, constitutionalism, and property in the body.

Benjamin Van Roy, 1995, The Harvard journal of minority public health.

Provably Efficient Reinforcement Learning with Aggregated States

Benjamin Van Roy, Zhengyuan Zhou, Shi Dong, 2019, ArXiv.

On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning

Noah D. Goodman, Benjamin Van Roy, Mark K. Ho, 2022, ArXiv.

Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning

Benjamin Van Roy, B. V. Roy, Dilip Arumugam, 2022, NeurIPS.

Inclusive Artificial Intelligence

Benjamin Van Roy, Dilip Arumugam, Shi Dong, 2022, ArXiv.

Bayesian Reinforcement Learning with Limited Cognitive Load

Noah D. Goodman, Benjamin Van Roy, Mark K. Ho, 2023, ArXiv.

Epistemic Neural Networks

Benjamin Van Roy, Zheng Wen, Ian Osband, 2021, ArXiv.

Leveraging Demonstrations to Improve Online Learning: Quality Matters

Benjamin Van Roy, Tor Lattimore, Botao Hao, 2023, ArXiv.

Fine-Tuning Language Models via Epistemic Neural Networks

Benjamin Van Roy, Ian Osband, J. Aslanides, 2022, ArXiv.

Evaluating High-Order Predictive Distributions in Deep Learning

Benjamin Van Roy, Zheng Wen, Ian Osband, 2022, UAI.

Leveraging Demonstrations to Improve Online Learning: Quality Matters

Benjamin Van Roy, Tor Lattimore, Botao Hao, 2023, ArXiv.

The Value of Information When Deciding What to Learn pdf

Benjamin Van Roy, Dilip Arumugam, Benjamin Van Roy, 2021, NeurIPS.

Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models

Benjamin Van Roy, Dilip Arumugam, Shi Dong, 2023, ArXiv.

A statistical–dynamical downscaling methodology for the urban heat island applied to the EURO-CORDEX ensemble

Benjamin Van Roy, A. Lemonsu, R. Schoetter, 2021, Climate Dynamics.

InP-based waveguides: comparison of ECR plasma etching and wet-chemical etching

Benjamin Van Roy, F. Karouta, C. Jagadish, 2000 .

InP surface damages after ECR dry etching

Benjamin Van Roy, F. Karouta, E. Smalbrugge, 1999 .

Managing the quality of a resource with stock and flow controls

Benjamin Van Roy, R. Zeckhauser, N. Keohane, 2007, Journal of Public Economics.

An Analysis of Ensemble Sampling

Benjamin Van Roy, Zheng Wen, Xiuyuan Lu, 2022, NeurIPS.

Scalable Neural Contextual Bandit for Recommender Systems

Benjamin Van Roy, Zheqing Zhu, 2023, arXiv.org.

Deep Exploration for Recommendation Systems

Benjamin Van Roy, Zheqing Zhu, 2021, arXiv.org.

The Neural Testbed: Evaluating Predictive Distributions

Benjamin Van Roy, Ian Osband, Dieterich Lawson, 2022 .

A Definition of Non-Stationary Bandits

Benjamin Van Roy, Kuang Xu, Yueyang Liu, 2023, ArXiv.

Nonstationary Bandit Learning via Predictive Sampling

Benjamin Van Roy, B. V. Roy, Kuang Xu, 2022, AISTATS.

Gaussian Imagination in Bandit Learning

Benjamin Van Roy, Adithya M. Devraj, Kuang Xu, 2022, ArXiv.

Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent States

Benjamin Van Roy, Zhengyuan Zhou, Shi Dong, 2021, J. Mach. Learn. Res..

On the existence of fixed points for approximate value iteration and temporal-difference learning

Benjamin Van Roy, D. D. Farias, B. V. Roy, 2000 .

On the Convergence of Bounded Agents

Benjamin Van Roy, Doina Precup, Satinder Singh, 2023, ArXiv.

Scalable Neural Contextual Bandit for Recommender Systems

Benjamin Van Roy, Zheqing Zhu, 2023, CIKM.

Deep Exploration for Recommendation Systems

Benjamin Van Roy, Zheqing Zhu, 2021, ArXiv.

Continual Learning as Computationally Constrained Reinforcement Learning

Benjamin Van Roy, Hong Jun Jeon, Saurabh Kumar, 2023, ArXiv.

Maintaining Plasticity via Regenerative Regularization

Benjamin Van Roy, Saurabh Kumar, H. Marklund, 2023, ArXiv.

A Definition of Continual Reinforcement Learning

Benjamin Van Roy, Doina Precup, André Barreto, 2023, ArXiv.

A Definition of Non-Stationary Bandits

Benjamin Van Roy, Kuang Xu, Yueyang Liu, 2023, ArXiv.

An Information-Theoretic Framework for Supervised Learning

Benjamin Van Roy, Hong Jun Jeon, 2022, 2203.00246.

Chapter 1 Control of Diffusions via Linear Programming

Benjamin Van Roy, Jiarui Han, 2008 .

Randomized Value Functions via Posterior State-Abstraction Sampling

Benjamin Van Roy, Dilip Arumugam, 2020, ArXiv.

Efficient Reinforcement Learning in Deterministic Systems with Value Function Generalization

Benjamin Van Roy, Zheng Wen, 2013, Mathematics of Operations Research.

A neuro-dynamic programming approach to retailer inventory management

Benjamin Van Roy, J.N. Tsitsiklis, B. Van Roy, 1997, Proceedings of the 36th IEEE Conference on Decision and Control.

An Analysis of Temporal-Difference Learning with Function Approximation

Benjamin Van Roy, J. Tsitsiklis, 1998 .

Approximate Thompson Sampling via Epistemic Neural Networks

Benjamin Van Roy, Ian Osband, Xiuyuan Lu, 2023, UAI.

Posterior Sampling for Continuing Environments

Benjamin Van Roy, Shi Dong, Wanqiao Xu, 2022, ArXiv.

Deep Exploration for Recommendation Systems

Benjamin Van Roy, Zheqing Zhu, 2021, RecSys.