Benjamin Van Roy

204 papers A* 24A 7B 2C 1Journal 140Unranked 29

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Consequentialist Objectives and Catastrophe. CoRR Henrik Marklund, Alex Infanger, Benjamin Van Roy
2026	J	`jnl`	Efficient Exploration at Scale. CoRR Seyed Mohammad Asghari, Chris Chute, Vikranth Dwaracherla, Xiuyuan Lu, Mehdi Jafarnia, Victor Minden, Zheng Wen, Benjamin Van Roy
2026	A*	`conf`	Misalignment from Treating Means as Ends. AAAI Henrik Marklund, Alex Infanger, Benjamin Van Roy
2026	J	`jnl`	Prior Diffusiveness and Regret in the Linear-Gaussian Bandit. CoRR Yifan Zhu, John C. Duchi, Benjamin Van Roy
2025	J	`jnl`	Capacity-Constrained Continual Learning. CoRR Zheng Wen, Doina Precup, Benjamin Van Roy, Satinder Singh
2025	J	`jnl`	Continual Learning as Computationally Constrained Reinforcement Learning. Found. Trends Mach. Learn. Saurabh Kumar, Henrik Marklund, Ashish Rao, Yifan Zhu, Hong Jun Jeon, Yueyang Liu, Benjamin Van Roy
2025	J	`jnl`	Granular feedback merits sophisticated aggregation. CoRR Anmol Kagrecha, Henrik Marklund, Potsawee Manakul, Richard Zeckhauser, Benjamin Van Roy
2025	J	`jnl`	Misalignment from Treating Means as Ends. CoRR Henrik Marklund, Alex Infanger, Benjamin Van Roy
2024	J	`jnl`	Adaptive Crowdsourcing Via Self-Supervised Learning. CoRR Anmol Kagrecha, Henrik Marklund, Benjamin Van Roy, Hong Jun Jeon, Richard Zeckhauser
2024	J	`jnl`	Aligning AI Agents via Information-Directed Sampling. CoRR Hong Jun Jeon, Benjamin Van Roy
2024	A*	`conf`	An Information-Theoretic Analysis of In-Context Learning. ICML Hong Jun Jeon, Jason D. Lee, Qi Lei, Benjamin Van Roy
2024	J	`jnl`	An Information-Theoretic Analysis of In-Context Learning. CoRR Hong Jun Jeon, Jason D. Lee, Qi Lei, Benjamin Van Roy
2024	J	`jnl`	Choice between Partial Trajectories. CoRR Henrik Marklund, Benjamin Van Roy
2024	A*	`conf`	Efficient Exploration for LLMs. ICML Vikranth Dwaracherla, Seyed Mohammad Asghari, Botao Hao, Benjamin Van Roy
2024	J	`jnl`	Efficient Exploration for LLMs. CoRR Vikranth Dwaracherla, Seyed Mohammad Asghari, Botao Hao, Benjamin Van Roy
2024	J	`jnl`	Exploration Unbound. CoRR Dilip Arumugam, Wanqiao Xu, Benjamin Van Roy
2024	J	`jnl`	Information-Theoretic Foundations for Machine Learning. CoRR Hong Jun Jeon, Benjamin Van Roy
2024	J	`jnl`	Information-Theoretic Foundations for Neural Scaling Laws. CoRR Hong Jun Jeon, Benjamin Van Roy
2024	—	`conf`	Langevin DQN. CDC Vikranth Dwaracherla, Benjamin Van Roy
2024	—	`conf`	Maintaining Plasticity in Continual Learning via Regenerative Regularization. CoLLAs Saurabh Kumar, Henrik Marklund, Benjamin Van Roy
2024	J	`jnl`	Posterior Sampling for Continuing Environments. RLJ Wanqiao Xu, Shi Dong, Benjamin Van Roy
2024	J	`jnl`	Satisficing Exploration for Deep Reinforcement Learning. CoRR Dilip Arumugam, Saurabh Kumar, Ramki Gummadi, Benjamin Van Roy
2024	J	`jnl`	The Need for a Big World Simulator: A Scientific Challenge for Continual Learning. CoRR Saurabh Kumar, Hong Jun Jeon, Alex Lewandowski, Benjamin Van Roy
2023	A*	`conf`	A Definition of Continual Reinforcement Learning. NeurIPS David Abel, André Barreto, Benjamin Van Roy, Doina Precup, Hado Philip van Hasselt, Satinder Singh
2023	J	`jnl`	A Definition of Continual Reinforcement Learning. CoRR David Abel, André Barreto, Benjamin Van Roy, Doina Precup, Hado van Hasselt, Satinder Singh
2023	J	`jnl`	A Definition of Non-Stationary Bandits. CoRR Yueyang Liu, Benjamin Van Roy, Kuang Xu
2023	A	`conf`	Approximate Thompson Sampling via Epistemic Neural Networks. UAI Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Morteza Ibrahimi, Xiuyuan Lu, Benjamin Van Roy
2023	J	`jnl`	Approximate Thompson Sampling via Epistemic Neural Networks. CoRR Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Morteza Ibrahimi, Xiuyuan Lu, Benjamin Van Roy
2023	J	`jnl`	Bayesian Reinforcement Learning with Limited Cognitive Load. CoRR Dilip Arumugam, Mark K. Ho, Noah D. Goodman, Benjamin Van Roy
2023	J	`jnl`	Continual Learning as Computationally Constrained Reinforcement Learning. CoRR Saurabh Kumar, Henrik Marklund, Ashish Rao, Yifan Zhu, Hong Jun Jeon, Yueyang Liu, Benjamin Van Roy
2023	A	`conf`	Deep Exploration for Recommendation Systems. RecSys Zheqing Zhu, Benjamin Van Roy
2023	J	`jnl`	Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrapping. Trans. Mach. Learn. Res. Vikranth Dwaracherla, Zheng Wen, Ian Osband, Xiuyuan Lu, Seyed Mohammad Asghari, Benjamin Van Roy
2023	A*	`conf`	Epistemic Neural Networks. NeurIPS Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Morteza Ibrahimi, Xiuyuan Lu, Benjamin Van Roy
2023	A*	`conf`	Leveraging Demonstrations to Improve Online Learning: Quality Matters. ICML Botao Hao, Rahul Jain, Tor Lattimore, Benjamin Van Roy, Zheng Wen
2023	J	`jnl`	Leveraging Demonstrations to Improve Online Learning: Quality Matters. CoRR Botao Hao, Rahul Jain, Tor Lattimore, Benjamin Van Roy, Zheng Wen
2023	J	`jnl`	Maintaining Plasticity via Regenerative Regularization. CoRR Saurabh Kumar, Henrik Marklund, Benjamin Van Roy
2023	J	`jnl`	Non-Stationary Contextual Bandit Learning via Neural Predictive Ensemble Sampling. CoRR Zheqing Zhu, Yueyang Liu, Xu Kuang, Benjamin Van Roy
2023	A	`conf`	Nonstationary Bandit Learning via Predictive Sampling. AISTATS Yueyang Liu, Benjamin Van Roy, Kuang Xu
2023	J	`jnl`	On the Convergence of Bounded Agents. CoRR David Abel, André Barreto, Hado van Hasselt, Benjamin Van Roy, Doina Precup, Satinder Singh
2023	J	`jnl`	RLHF and IIA: Perverse Incentives. CoRR Wanqiao Xu, Shi Dong, Xiuyuan Lu, Grace Lam, Zheng Wen, Benjamin Van Roy
2023	J	`jnl`	Reinforcement Learning, Bit by Bit. Found. Trends Mach. Learn. Xiuyuan Lu, Benjamin Van Roy, Vikranth Dwaracherla, Morteza Ibrahimi, Ian Osband, Zheng Wen
2023	A	`conf`	Scalable Neural Contextual Bandit for Recommender Systems. CIKM Zheqing Zhu, Benjamin Van Roy
2023	J	`jnl`	Scalable Neural Contextual Bandit for Recommender Systems. CoRR Zheqing Zhu, Benjamin Van Roy
2023	J	`jnl`	Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models. CoRR Wanqiao Xu, Shi Dong, Dilip Arumugam, Benjamin Van Roy
2022	A*	`conf`	An Analysis of Ensemble Sampling. NeurIPS Chao Qin, Zheng Wen, Xiuyuan Lu, Benjamin Van Roy
2022	J	`jnl`	An Analysis of Ensemble Sampling. CoRR Chao Qin, Zheng Wen, Xiuyuan Lu, Benjamin Van Roy
2022	J	`jnl`	An Information-Theoretic Analysis of Compute-Optimal Neural Scaling Laws. CoRR Hong Jun Jeon, Benjamin Van Roy
2022	A*	`conf`	An Information-Theoretic Framework for Deep Learning. NeurIPS Hong Jun Jeon, Benjamin Van Roy
2022	J	`jnl`	Between Rate-Distortion Theory & Value Equivalence in Model-Based Reinforcement Learning. CoRR Dilip Arumugam, Benjamin Van Roy
2022	A*	`conf`	Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning. NeurIPS Dilip Arumugam, Benjamin Van Roy
2022	J	`jnl`	Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning. CoRR Dilip Arumugam, Benjamin Van Roy
2022	J	`jnl`	Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrapping. CoRR Vikranth Dwaracherla, Zheng Wen, Ian Osband, Xiuyuan Lu, Seyed Mohammad Asghari, Benjamin Van Roy
2022	J	`jnl`	Evaluating High-Order Predictive Distributions in Deep Learning. CoRR Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Xiuyuan Lu, Benjamin Van Roy
2022	A	`conf`	Evaluating high-order predictive distributions in deep learning. UAI Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Xiuyuan Lu, Benjamin Van Roy
2022	J	`jnl`	Fine-Tuning Language Models via Epistemic Neural Networks. CoRR Ian Osband, Seyed Mohammad Asghari, Benjamin Van Roy, Nat McAleese, John Aslanides, Geoffrey Irving
2022	J	`jnl`	Gaussian Imagination in Bandit Learning. CoRR Yueyang Liu, Adithya M. Devraj, Benjamin Van Roy, Kuang Xu
2022	J	`jnl`	Inclusive Artificial Intelligence. CoRR Dilip Arumugam, Shi Dong, Benjamin Van Roy
2022	J	`jnl`	Is Stochastic Gradient Descent Near Optimal? CoRR Yifan Zhu, Hong Jun Jeon, Benjamin Van Roy
2022	J	`jnl`	Nonstationary Bandit Learning via Predictive Sampling. CoRR Yueyang Liu, Benjamin Van Roy, Kuang Xu
2022	J	`jnl`	On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning. CoRR Dilip Arumugam, Mark K. Ho, Noah D. Goodman, Benjamin Van Roy
2022	J	`jnl`	Posterior Sampling for Continuing Environments. CoRR Wanqiao Xu, Shi Dong, Benjamin Van Roy
2022	J	`jnl`	Robustness of Epinets against Distributional Shifts. CoRR Xiuyuan Lu, Ian Osband, Seyed Mohammad Asghari, Sven Gowal, Vikranth Dwaracherla, Zheng Wen, Benjamin Van Roy
2022	J	`jnl`	Sample Complexity versus Depth: An Information Theoretic Analysis. CoRR Hong Jun Jeon, Benjamin Van Roy
2022	J	`jnl`	Satisficing in Time-Sensitive Bandit Learning. Math. Oper. Res. Daniel Russo, Benjamin Van Roy
2022	J	`jnl`	Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent States. J. Mach. Learn. Res. Shi Dong, Benjamin Van Roy, Zhengyuan Zhou
2022	A*	`conf`	The Neural Testbed: Evaluating Joint Predictions. NeurIPS Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Xiuyuan Lu, Morteza Ibrahimi, Dieterich Lawson, Botao Hao, Brendan O'Donoghue, Benjamin Van Roy
2021	J	`jnl`	A Bit Better? Quantifying Information for Bandit Learning. CoRR Adithya M. Devraj, Benjamin Van Roy, Kuang Xu
2021	A*	`conf`	Deciding What to Learn: A Rate-Distortion Approach. ICML Dilip Arumugam, Benjamin Van Roy
2021	J	`jnl`	Deciding What to Learn: A Rate-Distortion Approach. CoRR Dilip Arumugam, Benjamin Van Roy
2021	J	`jnl`	Deep Exploration for Recommendation Systems. CoRR Zheqing Zhu, Benjamin Van Roy
2021	J	`jnl`	Epistemic Neural Networks. CoRR Ian Osband, Zheng Wen, Mohammad Asghari, Morteza Ibrahimi, Xiyuan Lu, Benjamin Van Roy
2021	J	`jnl`	Evaluating Predictive Distributions: Does Bayesian Deep Learning Work? CoRR Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Botao Hao, Morteza Ibrahimi, Dieterich Lawson, Xiuyuan Lu, Brendan O'Donoghue, Benjamin Van Roy
2021	J	`jnl`	Evaluating Probabilistic Inference in Deep Learning: Beyond Marginal Predictions. CoRR Xiuyuan Lu, Ian Osband, Benjamin Van Roy, Zheng Wen
2021	J	`jnl`	Reinforcement Learning, Bit by Bit. CoRR Xiuyuan Lu, Benjamin Van Roy, Vikranth Dwaracherla, Morteza Ibrahimi, Ian Osband, Zheng Wen
2021	J	`jnl`	Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent State. CoRR Shi Dong, Benjamin Van Roy, Zhengyuan Zhou
2021	A*	`conf`	The Value of Information When Deciding What to Learn. NeurIPS Dilip Arumugam, Benjamin Van Roy
2021	J	`jnl`	The Value of Information When Deciding What to Learn. CoRR Dilip Arumugam, Benjamin Van Roy
2020	A*	`conf`	Behaviour Suite for Reinforcement Learning. ICLR Ian Osband, Yotam Doron, Matteo Hessel, John Aslanides, Eren Sezener, Andre Saraiva, Katrina McKinney, Tor Lattimore, Csaba Szepesvári, Satinder Singh, Benjamin Van Roy, Richard S. Sutton, David Silver, Hado van Hasselt
2020	A*	`conf`	Hypermodels for Exploration. ICLR Vikranth Dwaracherla, Xiuyuan Lu, Morteza Ibrahimi, Ian Osband, Zheng Wen, Benjamin Van Roy
2020	J	`jnl`	Hypermodels for Exploration. CoRR Vikranth Dwaracherla, Xiuyuan Lu, Morteza Ibrahimi, Ian Osband, Zheng Wen, Benjamin Van Roy
2020	J	`jnl`	Langevin DQN. CoRR Vikranth Dwaracherla, Benjamin Van Roy
2020	A*	`conf`	On Efficiency in Hierarchical Reinforcement Learning. NeurIPS Zheng Wen, Doina Precup, Morteza Ibrahimi, André Barreto, Benjamin Van Roy, Satinder Singh
2020	J	`jnl`	Randomized Value Functions via Posterior State-Abstraction Sampling. CoRR Dilip Arumugam, Benjamin Van Roy
2019	J	`jnl`	Behaviour Suite for Reinforcement Learning. CoRR Ian Osband, Yotam Doron, Matteo Hessel, John Aslanides, Eren Sezener, Andre Saraiva, Katrina McKinney, Tor Lattimore, Csaba Szepesvári, Satinder Singh, Benjamin Van Roy, Richard S. Sutton, David Silver, Hado van Hasselt
2019	J	`jnl`	Comments on the Du-Kakade-Wang-Yang Lower Bounds. CoRR Benjamin Van Roy, Shi Dong
2019	J	`jnl`	Deep Exploration via Randomized Value Functions. J. Mach. Learn. Res. Ian Osband, Benjamin Van Roy, Daniel J. Russo, Zheng Wen
2019	A*	`conf`	Information-Theoretic Confidence Bounds for Reinforcement Learning. NeurIPS Xiuyuan Lu, Benjamin Van Roy
2019	J	`jnl`	Information-Theoretic Confidence Bounds for Reinforcement Learning. CoRR Xiuyuan Lu, Benjamin Van Roy
2019	A*	`conf`	On the Performance of Thompson Sampling on Logistic Bandits. COLT Shi Dong, Tengyu Ma, Benjamin Van Roy
2019	J	`jnl`	On the Performance of Thompson Sampling on Logistic Bandits. CoRR Shi Dong, Tengyu Ma, Benjamin Van Roy
2019	J	`jnl`	Provably Efficient Reinforcement Learning with Aggregated States. CoRR Shi Dong, Benjamin Van Roy, Zhengyuan Zhou
2018	J	`jnl`	A Tutorial on Thompson Sampling. Found. Trends Mach. Learn. Daniel Russo, Benjamin Van Roy, Abbas Kazerouni, Ian Osband, Zheng Wen
2018	A*	`conf`	An Information-Theoretic Analysis for Thompson Sampling with Many Actions. NeurIPS Shi Dong, Benjamin Van Roy
2018	J	`jnl`	An Information-Theoretic Analysis of Thompson Sampling for Large Action Spaces. CoRR Shi Dong, Benjamin Van Roy
2018	A*	`conf`	Coordinated Exploration in Concurrent Reinforcement Learning. ICML Maria Dimakopoulou, Benjamin Van Roy
2018	J	`jnl`	Coordinated Exploration in Concurrent Reinforcement Learning. CoRR Maria Dimakopoulou, Benjamin Van Roy
2018	J	`jnl`	Learning to Optimize via Information-Directed Sampling. Oper. Res. Daniel Russo, Benjamin Van Roy
2018	J	`jnl`	Satisficing in Time-Sensitive Bandit Learning. CoRR Daniel Russo, Benjamin Van Roy
2018	A*	`conf`	Scalable Coordinated Exploration in Concurrent Reinforcement Learning. NeurIPS Maria Dimakopoulou, Ian Osband, Benjamin Van Roy
2018	J	`jnl`	Scalable Coordinated Exploration in Concurrent Reinforcement Learning. CoRR Maria Dimakopoulou, Ian Osband, Benjamin Van Roy
2017	J	`jnl`	A Tutorial on Thompson Sampling. CoRR Daniel Russo, Benjamin Van Roy, Abbas Kazerouni, Ian Osband
2017	—	`conf`	Conservative Contextual Linear Bandits. NIPS Abbas Kazerouni, Mohammad Ghavamzadeh, Yasin Abbasi, Benjamin Van Roy
2017	J	`jnl`	Deep Exploration via Randomized Value Functions. CoRR Ian Osband, Daniel Russo, Zheng Wen, Benjamin Van Roy
2017	J	`jnl`	Efficient Reinforcement Learning in Deterministic Systems with Value Function Generalization. Math. Oper. Res. Zheng Wen, Benjamin Van Roy
2017	—	`conf`	Ensemble Sampling. NIPS Xiuyuan Lu, Benjamin Van Roy
2017	J	`jnl`	Ensemble Sampling. CoRR Xiuyuan Lu, Benjamin Van Roy
2017	J	`jnl`	Gaussian-Dirichlet Posterior Dominance in Sequential Learning. CoRR Ian Osband, Benjamin Van Roy
2017	J	`jnl`	Learning to Price with Reference Effects. CoRR Abbas Kazerouni, Benjamin Van Roy
2017	J	`jnl`	On Optimistic versus Randomized Exploration in Reinforcement Learning. CoRR Ian Osband, Benjamin Van Roy
2017	J	`jnl`	Time-Sensitive Bandit Learning and Satisficing Thompson Sampling. CoRR Daniel Russo, David Tse, Benjamin Van Roy
2017	A*	`conf`	Why is Posterior Sampling Better than Optimism for Reinforcement Learning? ICML Ian Osband, Benjamin Van Roy
2016	J	`jnl`	An Information-Theoretic Analysis of Thompson Sampling. J. Mach. Learn. Res. Daniel Russo, Benjamin Van Roy
2016	J	`jnl`	Conservative Contextual Linear Bandits. CoRR Abbas Kazerouni, Mohammad Ghavamzadeh, Benjamin Van Roy
2016	—	`conf`	Deep Exploration via Bootstrapped DQN. NIPS Ian Osband, Charles Blundell, Alexander Pritzel, Benjamin Van Roy
2016	J	`jnl`	Deep Exploration via Bootstrapped DQN. CoRR Ian Osband, Charles Blundell, Alexander Pritzel, Benjamin Van Roy
2016	A*	`conf`	Generalization and Exploration via Randomized Value Functions. ICML Ian Osband, Benjamin Van Roy, Zheng Wen
2016	J	`jnl`	On Lower Bounds for Regret in Reinforcement Learning. CoRR Ian Osband, Benjamin Van Roy
2016	J	`jnl`	Posterior Sampling for Reinforcement Learning Without Episodes. CoRR Ian Osband, Benjamin Van Roy
2016	J	`jnl`	Why is Posterior Sampling Better than Optimism for Reinforcement Learning. CoRR Ian Osband, Benjamin Van Roy
2015	J	`jnl`	Adaptive Execution: Exploration and Learning of Price Impact. Oper. Res. Beomsoo Park, Benjamin Van Roy
2015	J	`jnl`	Bootstrapped Thompson Sampling and Deep Exploration. CoRR Ian Osband, Benjamin Van Roy
2014	J	`jnl`	An Information-Theoretic Analysis of Thompson Sampling. CoRR Daniel Russo, Benjamin Van Roy
2014	J	`jnl`	Directed Principal Component Analysis. Oper. Res. Yi-Hao Kao, Benjamin Van Roy
2014	J	`jnl`	Generalization and Exploration via Randomized Value Functions. CoRR Benjamin Van Roy, Zheng Wen
2014	J	`jnl`	Learning to Optimize Via Information Directed Sampling. CoRR Daniel Russo, Benjamin Van Roy
2014	—	`conf`	Learning to Optimize via Information-Directed Sampling. NIPS Daniel Russo, Benjamin Van Roy
2014	J	`jnl`	Learning to Optimize via Posterior Sampling. Math. Oper. Res. Daniel Russo, Benjamin Van Roy
2014	—	`conf`	Model-based Reinforcement Learning and the Eluder Dimension. NIPS Ian Osband, Benjamin Van Roy
2014	J	`jnl`	Model-based Reinforcement Learning and the Eluder Dimension. CoRR Ian Osband, Benjamin Van Roy
2014	J	`jnl`	Near-optimal Regret Bounds for Reinforcement Learning in Factored MDPs. CoRR Ian Osband, Benjamin Van Roy
2014	—	`conf`	Near-optimal Reinforcement Learning in Factored MDPs. NIPS Ian Osband, Benjamin Van Roy
2013	—	`conf`	(More) Efficient Reinforcement Learning via Posterior Sampling. NIPS Ian Osband, Daniel Russo, Benjamin Van Roy
2013	J	`jnl`	(More) Efficient Reinforcement Learning via Posterior Sampling. CoRR Ian Osband, Daniel Russo, Benjamin Van Roy
2013	J	`jnl`	A Tractable POMDP for a Class of Sequencing Problems CoRR Paat Rusmevichientong, Benjamin Van Roy
2013	—	`conf`	Efficient Exploration and Value Function Generalization in Deterministic Systems. NIPS Zheng Wen, Benjamin Van Roy
2013	J	`jnl`	Efficient Exploration and Value Function Generalization in Deterministic Systems. CoRR Zheng Wen, Benjamin Van Roy
2013	J	`jnl`	Efficient Reinforcement Learning for High Dimensional Linear Quadratic Systems CoRR Morteza Ibrahimi, Adel Javanmard, Benjamin Van Roy
2013	—	`conf`	Eluder Dimension and the Sample Complexity of Optimistic Exploration. NIPS Daniel Russo, Benjamin Van Roy
2013	J	`jnl`	Learning a factor model via regularized PCA. Mach. Learn. Yi-Hao Kao, Benjamin Van Roy
2013	J	`jnl`	Learning to Optimize Via Posterior Sampling CoRR Daniel Russo, Benjamin Van Roy
2012	J	`jnl`	A Hybrid Method for Distance Metric Learning. CoRR Yi-Hao Kao, Benjamin Van Roy, Daniel L. Rubin, Jiajing Xu, Jessica S. Faruque, Sandy Napel
2012	J	`jnl`	Directed Time Series Regression for Control CoRR Yi-Hao Kao, Benjamin Van Roy
2012	—	`conf`	Efficient Reinforcement Learning for High Dimensional Linear Quadratic Systems. NIPS Morteza Ibrahimi, Adel Javanmard, Benjamin Van Roy
2012	J	`jnl`	Intermediated Blind Portfolio Auctions. Manag. Sci. Michael Padilla, Benjamin Van Roy
2011	J	`jnl`	Industry dynamics: Foundations for models with an infinite number of firms. J. Econ. Theory Gabriel Y. Weintraub, C. Lanier Benkard, Benjamin Van Roy
2011	J	`jnl`	Learning a Factor Model via Regularized PCA CoRR Yi-Hao Kao, Benjamin Van Roy
2011	J	`jnl`	Resource Allocation via Message Passing. INFORMS J. Comput. Ciamac Cyrus Moallemi, Benjamin Van Roy
2010	J	`jnl`	Computational Methods for Oblivious Equilibrium. Oper. Res. Gabriel Y. Weintraub, C. Lanier Benkard, Benjamin Van Roy
2010	J	`jnl`	Convergence of min-sum message-passing for convex optimization. IEEE Trans. Inf. Theory Ciamac Cyrus Moallemi, Benjamin Van Roy
2010	J	`jnl`	Dynamic Pricing with a Prior on Market Response. Oper. Res. Vivek F. Farias, Benjamin Van Roy
2010	J	`jnl`	Investment and Market Structure in Industries with Congestion. Oper. Res. Ramesh Johari, Gabriel Y. Weintraub, Benjamin Van Roy
2010	J	`jnl`	Manipulation Robustness of Collaborative Filtering. Manag. Sci. Benjamin Van Roy, Xiang Yan
2010	J	`jnl`	On Regression-Based Stopping Times. Discret. Event Dyn. Syst. Benjamin Van Roy
2010	J	`jnl`	Universal reinforcement learning. IEEE Trans. Inf. Theory Vivek F. Farias, Ciamac Cyrus Moallemi, Benjamin Van Roy, Tsachy Weissman
2009	J	`jnl`	Convergence of min-sum message passing for quadratic optimization. IEEE Trans. Inf. Theory Ciamac Cyrus Moallemi, Benjamin Van Roy
2009	—	`conf`	Directed Regression. NIPS Yi-Hao Kao, Benjamin Van Roy, Xiang Yan
2009	J	`jnl`	Manipulation Robustness of Collaborative Filtering Systems CoRR Xiang Yan, Benjamin Van Roy
2009	A	`conf`	Manipulation-resistant collaborative filtering systems. RecSys Benjamin Van Roy, Xiang Yan
2008	J	`jnl`	Capacity of the Trapdoor Channel With Feedback. IEEE Trans. Inf. Theory Haim H. Permuter, Paul Cuff, Benjamin Van Roy, Tsachy Weissman
2008	—	`conf`	Reputation markets. NetEcon Xiang Yan, Benjamin Van Roy
2007	J	`jnl`	A short proof of optimality for the MIN cache replacement algorithm. Inf. Process. Lett. Benjamin Van Roy
2007	B	`conf`	Capacity and Zero-Error Capacity of the Chemical Channel with Feedback. ISIT Haim H. Permuter, Paul Cuff, Benjamin Van Roy, Tsachy Weissman
2007	J	`jnl`	Universal Reinforcement Learning CoRR Vivek F. Farias, Ciamac Cyrus Moallemi, Tsachy Weissman, Benjamin Van Roy
2006	J	`jnl`	A Cost-Shaping Linear Program for Average-Cost Approximate Dynamic Programming with Performance Guarantees. Math. Oper. Res. Daniela Pucci de Farias, Benjamin Van Roy
2006	J	`jnl`	A Generalized Kalman Filter for Fixed Point Approximation and Efficient Temporal-Difference Learning. Discret. Event Dyn. Syst. David Choi, Benjamin Van Roy
2006	J	`jnl`	A Nonparametric Approach to Multiproduct Pricing. Oper. Res. Paat Rusmevichientong, Benjamin Van Roy, Peter W. Glynn
2006	J	`jnl`	Approximation algorithms for dynamic resource allocation. Oper. Res. Lett. Vivek F. Farias, Benjamin Van Roy
2006	J	`jnl`	Capacity of the Trapdoor Channel with Feedback CoRR Haim H. Permuter, Paul Cuff, Benjamin Van Roy, Tsachy Weissman
2006	J	`jnl`	Consensus Propagation CoRR Ciamac Cyrus Moallemi, Benjamin Van Roy
2006	J	`jnl`	Consensus Propagation. IEEE Trans. Inf. Theory Ciamac Cyrus Moallemi, Benjamin Van Roy
2006	J	`jnl`	Convergence of the Min-Sum Message Passing Algorithm for Quadratic Optimization CoRR Ciamac Cyrus Moallemi, Benjamin Van Roy
2006	J	`jnl`	Performance Loss Bounds for Approximate Value Iteration with State Aggregation. Math. Oper. Res. Benjamin Van Roy
2005	B	`conf`	A universal scheme for learning. ISIT Vivek F. Farias, Ciamac C. Moallemi, Benjamin Van Roy, Tsachy Weissman
2005	—	`conf`	Consensus Propagation. NIPS Ciamac Cyrus Moallemi, Benjamin Van Roy
2005	—	`conf`	Oblivious Equilibrium: A Mean Field Approximation for Large-Scale Dynamic Games. NIPS Gabriel Y. Weintraub, C. Lanier Benkard, Benjamin Van Roy
2005	—	`conf`	TD(0) Leads to Better Policies than Approximate Value Iteration. NIPS Benjamin Van Roy
2004	—	`conf`	A Cost-Shaping LP for Bellman Error Minimization with Performance Guarantees. NIPS Daniela Pucci de Farias, Benjamin Van Roy
2004	C	`conf`	Making Eigenvector-Based Reputation Systems Robust to Collusion. WAW Hui Zhang, Ashish Goel, Ramesh Govindan, Kahn Mason, Benjamin Van Roy
2004	J	`jnl`	On Constraint Sampling in the Linear Programming Approach to Approximate Dynamic Programming. Math. Oper. Res. Daniela Pucci de Farias, Benjamin Van Roy
2004	—	`conf`	Solitaire: Man Versus Machine. NIPS Xiang Yan, Persi Diaconis, Paat Rusmevichientong, Benjamin Van Roy
2003	J	`jnl`	Decentralized decision-making in a large team with local information. Games Econ. Behav. Paat Rusmevichientong, Benjamin Van Roy
2003	—	`conf`	Distributed Optimization in Adaptive Networks. NIPS Ciamac Cyrus Moallemi, Benjamin Van Roy
2003	—	`conf`	On constraint sampling in the linear programming approach to approximate linear programming. CDC Daniela Pucci de Farias, Benjamin Van Roy
2003	J	`jnl`	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. Autom. Benjamin Van Roy
2003	J	`jnl`	The Linear Programming Approach to Approximate Dynamic Programming. Oper. Res. Daniela Pucci de Farias, Benjamin Van Roy
2002	—	`conf`	Approximate Linear Programming for Average-Cost Dynamic Programming. NIPS Daniela Pucci de Farias, Benjamin Van Roy
2002	J	`jnl`	On Average Versus Discounted Reward Temporal-Difference Learning. Mach. Learn. John N. Tsitsiklis, Benjamin Van Roy
2001	A*	`conf`	A Generalized Kalman Filter for Fixed Point Approximation and Efficient Temporal Difference Learning. ICML David Choi, Benjamin Van Roy
2001	A	`conf`	A Tractable POMDP for Dynamic Sequencing with Applications to Personalized Internet Content Provision. UAI Paat Rusmevichientong, Benjamin Van Roy
2001	J	`jnl`	An analysis of belief propagation on the turbo decoding graph with Gaussian densities. IEEE Trans. Inf. Theory Paat Rusmevichientong, Benjamin Van Roy
2001	—	`conf`	Approximate Dynamic Programming via Linear Programming. NIPS Daniela Pucci de Farias, Benjamin Van Roy
2001	J	`jnl`	Regression methods for pricing complex American-style options. IEEE Trans. Neural Networks John N. Tsitsiklis, Benjamin Van Roy
2000	—	`conf`	Approximate value iteration with randomized policies. CDC Daniela Pucci de Farias, Benjamin Van Roy
2000	A*	`conf`	Fixed Points of Approximate Value Iteration and Temporal-Difference Learning. ICML Daniela Pucci de Farias, Benjamin Van Roy
2000	—	`conf`	The optimal harvesting of environmental bads. CDC Nathaniel Keohane, Benjamin Van Roy, Richard Zeckhauser
1999	—	`conf`	An Analysis of Turbo Decoding with Gaussian Densities. NIPS Paat Rusmevichientong, Benjamin Van Roy
1999	J	`jnl`	Average cost temporal-difference learning. Autom. John N. Tsitsiklis, Benjamin Van Roy
1999	J	`jnl`	Optimal stopping of Markov processes: Hilbert space theory, approximation algorithms, and an application to pricing high-dimensional financial derivatives. IEEE Trans. Autom. Control. John N. Tsitsiklis, Benjamin Van Roy
1998	—	`—`	Learning and value function approximation in complex decision processes. Benjamin Van Roy
1997	J	`jnl`	An analysis of temporal-difference learning with function approximation. IEEE Trans. Autom. Control. John N. Tsitsiklis, Benjamin Van Roy
1996	—	`conf`	Analysis of Temporal-Diffference Learning with Function Approximation. NIPS John N. Tsitsiklis, Benjamin Van Roy
1996	—	`conf`	Approximate Solutions to Optimal Stopping Problems. NIPS John N. Tsitsiklis, Benjamin Van Roy
1996	J	`jnl`	Feature-Based Methods for Large Scale Dynamic Programming. Mach. Learn. John N. Tsitsiklis, Benjamin Van Roy
1995	—	`conf`	Stable LInear Approximations to Dynamic Programming for Stochastic Control Problems with Local Transitions. NIPS Benjamin Van Roy, John N. Tsitsiklis