← Authors

Benjamin Van Roy

37 papers · 2013–2026 · 8 conferences · across top CS/AI conferences

Achievements

πŸ—ΊοΈ Taxonomy Completionist (12) 🐝 Cross-Pollinator (12) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (7) πŸƒ Academic Marathon (11) 🌈 Renaissance Researcher (5) 🏠 Conference Loyalist (20) πŸ† Grand Slam πŸ”¬ Deep Specialist (13) 🀝 Dynamic Duo (14) πŸ† Keyword Champion (3) πŸ—ƒοΈ Keyword Collector (104) ❓ The Questioner ⚑ Prolific Year (6) πŸ“ˆ Trend Setter πŸ’Ž Century Club (36) πŸ”₯ Unstoppable (9)

Conferences

NIPS (20) ICML (7) JMLR (3) ICLR (2) UAI (2) AAAI (1) AISTATS (1) COLT (1)

Top co-authors

Ian Osband (14) Zheng Wen (11) Xiuyuan Lu (8) Vikranth Dwaracherla (6) Morteza Ibrahimi (5) Seyed Mohammad Asghari (5) Daniel Russo (4) Dilip Arumugam (3) Botao Hao (3) Shi Dong (3)

Keywords

regret bound (17) thompson sampling (11) reinforcement learning (10) multi-armed bandit (6) information theory (6) bayesian regret (6) posterior sampling (5) markov decision process (4) neural network (3) randomized value function (3) rate-distortion theory (3) optimistic exploration (3) eluder dimension (3) joint prediction (3) sequential decision making (2) online optimization (2) exploration (2) function approximation (2) bayesian inference (2) model-based reinforcement learning (2)

Papers

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