Benjamin Van Roy

Misalignment from Treating Means as Ends AAAI 2026 An Information-Theoretic Analysis of In-Context Learning ICML 2024 Efficient Exploration for LLMs ICML 2024 A Definition of Continual Reinforcement Learning NeurIPS 2023 Approximate Thompson Sampling via Epistemic Neural Networks UAI 2023 Epistemic Neural Networks NeurIPS 2023 Leveraging Demonstrations to Improve Online Learning: Quality Matters ICML 2023 Nonstationary Bandit Learning via Predictive Sampling AISTATS 2023 An Analysis of Ensemble Sampling NeurIPS 2022 An Information-Theoretic Framework for Deep Learning NeurIPS 2022 Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning NeurIPS 2022 Evaluating high-order predictive distributions in deep learning UAI 2022 Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent States JMLR 2022 The Neural Testbed: Evaluating Joint Predictions NeurIPS 2022 Deciding What to Learn: A Rate-Distortion Approach ICML 2021 The Value of Information When Deciding What to Learn NeurIPS 2021 Behaviour Suite for Reinforcement Learning ICLR 2020 Hypermodels for Exploration ICLR 2020 On Efficiency in Hierarchical Reinforcement Learning NeurIPS 2020 Deep Exploration via Randomized Value Functions JMLR 2019 Information-Theoretic Confidence Bounds for Reinforcement Learning NeurIPS 2019 On the Performance of Thompson Sampling on Logistic Bandits COLT 2019 An Information-Theoretic Analysis for Thompson Sampling with Many Actions NeurIPS 2018 Coordinated Exploration in Concurrent Reinforcement Learning ICML 2018 Scalable Coordinated Exploration in Concurrent Reinforcement Learning NeurIPS 2018 Conservative Contextual Linear Bandits NeurIPS 2017 Ensemble Sampling NeurIPS 2017 Why is Posterior Sampling Better than Optimism for Reinforcement Learning? ICML 2017 An Information-Theoretic Analysis of Thompson Sampling JMLR 2016 Deep Exploration via Bootstrapped DQN NeurIPS 2016 Generalization and Exploration via Randomized Value Functions ICML 2016 Learning to Optimize via Information-Directed Sampling NeurIPS 2014 Model-based Reinforcement Learning and the Eluder Dimension NeurIPS 2014 Near-optimal Reinforcement Learning in Factored MDPs NeurIPS 2014 Efficient Exploration and Value Function Generalization in Deterministic Systems NeurIPS 2013 Eluder Dimension and the Sample Complexity of Optimistic Exploration NeurIPS 2013 (More) Efficient Reinforcement Learning via Posterior Sampling NeurIPS 2013