BR
Benjamin Van Roy
cs.LGcs.AIstat.MLcs.ITmath.ITcs.SYeess.SYmath.OCcs.CLcs.IR
On Valency
published · living versionsW_gggmts3a·v1 · currentpublished
W_zs59fjhv·v1published
W_caxh5thz·v1published
Preprints & journals
102 papers in the corpus · 2001–2026OpenAI-HuggingFace: A Reproduction & Lessons for Alignment Testing2609.35799v1 · Stewart Slocum, Malayandi Palan, Christopher Chute et al.2026 · 0 citationsarXiv
An Information-Theoretic Definition for Open-Ended Learning2606.08369v1 · Wanqiao Xu, Yifan Zhu, Benjamin Van Roy2026 · 0 citationsarXiv
Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems2606.00367v2 · Jonathan Colaco Carr, Prakash Panangaden, Doina Precup et al.2026 · 0 citationsarXiv
Efficient Exploration at Scale2603.17378v2 · Seyed Mohammad Asghari, Chris Chute, Vikranth Dwaracherla et al.2026 · 0 citationsarXiv
Consequentialist Objectives and Catastrophe2603.15017v3 · Henrik Marklund, Alex Infanger, Benjamin Van Roy2026 · 0 citationsarXiv
Prior Diffusiveness and Regret in the Linear-Gaussian Bandit2601.02022v2 · Yifan Zhu, John C. Duchi, Benjamin Van Roy2026 · 0 citationsarXiv
Capacity-Constrained Continual Learning2507.21479v1 · Zheng Wen, Doina Precup, Benjamin Van Roy et al.2025 · 0 citationsarXiv
Granular feedback merits sophisticated aggregation2507.12041v1 · Anmol Kagrecha, Henrik Marklund, Potsawee Manakul et al.2025 · 0 citationsarXiv
Misalignment from Treating Means as Ends2507.10995v1 · Henrik Marklund, Alex Infanger, Benjamin Van Roy2025 · 0 citationsarXiv
Choice Between Partial Trajectories: Disentangling Goals from Beliefs2410.22690v3 · Henrik Marklund, Benjamin Van Roy2024 · 0 citationsarXiv
Aligning AI Agents via Information-Directed Sampling2410.14807v1 · Hong Jun Jeon, Benjamin Van Roy2024 · 0 citationsarXiv
The Need for a Big World Simulator: A Scientific Challenge for Continual Learning2408.02930v1 · Saurabh Kumar, Hong Jun Jeon, Alex Lewandowski et al.2024 · 0 citationsarXiv
Information-Theoretic Foundations for Machine Learning2407.12288v5 · Hong Jun Jeon, Benjamin Van Roy2024 · 2 citationsarXiv
Exploration Unbound2407.12178v1 · Dilip Arumugam, Wanqiao Xu, Benjamin Van Roy2024 · 0 citationsarXiv
Satisficing Exploration for Deep Reinforcement Learning2407.12185v1 · Dilip Arumugam, Saurabh Kumar, Ramki Gummadi et al.2024 · 0 citationsarXiv
Information-Theoretic Foundations for Neural Scaling Laws2407.01456v1 · Hong Jun Jeon, Benjamin Van Roy2024 · 0 citationsarXiv
Bayesian Reinforcement Learning With Limited Cognitive Load.38665544 · Arumugam, Dilip, Ho, Mark K, Goodman, Noah D et al.2024 · 12 citationsOpen mind : discoveries in cognitive science. 2024;8:395-438
Efficient Exploration for LLMs2402.00396v2 · Vikranth Dwaracherla, Seyed Mohammad Asghari, Botao Hao et al.2024 · 0 citationsarXiv
An Information-Theoretic Analysis of In-Context Learning2401.15530v1 · Hong Jun Jeon, Jason D. Lee, Qi Lei et al.2024 · 1 citationarXiv
Adaptive Crowdsourcing Via Self-Supervised Learning2401.13239v2 · Anmol Kagrecha, Henrik Marklund, Benjamin Van Roy et al.2024 · 0 citationsarXiv
RLHF and IIA: Perverse Incentives2312.01057v3 · Wanqiao Xu, Shi Dong, Xiuyuan Lu et al.2023 · 0 citationsarXiv
Non-Stationary Contextual Bandit Learning via Neural Predictive Ensemble Sampling2310.07786v2 · Zheqing Zhu, Yueyang Liu, Xu Kuang et al.2023 · 0 citationsarXiv
Maintaining Plasticity in Continual Learning via Regenerative Regularization2308.11958v3 · Saurabh Kumar, Henrik Marklund, Benjamin Van Roy2023 · 2 citationsarXiv
On the Convergence of Bounded Agents2307.11044v1 · David Abel, Andr'e Barreto, Hado van Hasselt et al.2023 · 0 citationsarXiv
A Definition of Continual Reinforcement Learning2307.11046v2 · David Abel, Andr'e Barreto, Benjamin Van Roy et al.2023 · 36 citationsarXiv
Continual Learning as Computationally Constrained Reinforcement Learning2307.04345v3 · Saurabh Kumar, Henrik Marklund, Ashish Rao et al.2023 · 4 citationsarXiv
Scalable Neural Contextual Bandit for Recommender Systems2306.14834v3 · Zheqing Zhu, Benjamin Van Roy2023 · 4 citationsACM International Conference on Information and Knowledge Management (CIKM 2023) 32nd ACM International Conference on Information and Knowledge Management (CIKM 2023)
Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models2305.11455v1 · Wanqiao Xu, Shi Dong, Dilip Arumugam et al.2023 · 0 citationsarXiv
A Definition of Non-Stationary Bandits2302.12202v2 · Yueyang Liu, Xu Kuang, Benjamin Van Roy2023 · 2 citationsarXiv
Approximate Thompson Sampling via Epistemic Neural Networks2302.09205v1 · Ian Osband, Zheng Wen, Seyed Mohammad Asghari et al.2023 · 1 citationarXiv
Leveraging Demonstrations to Improve Online Learning: Quality Matters2302.03319v4 · Botao Hao, Rahul Jain, Tor Lattimore et al.2023 · 0 citationsarXiv
Inclusive Artificial Intelligence2212.12633v2 · Dilip Arumugam, Shi Dong, Benjamin Van Roy2022 · 0 citationsarXiv
An Information-Theoretic Analysis of Compute-Optimal Neural Scaling Laws2212.01365v2 · Hong Jun Jeon, Benjamin Van Roy2022 · 0 citationsarXiv
Posterior Sampling for Continuing Environments2211.15931v4 · Wanqiao Xu, Shi Dong, Benjamin Van Roy2022 · 0 citationsarXiv
Fine-Tuning Language Models via Epistemic Neural Networks2211.01568v2 · Ian Osband, Seyed Mohammad Asghari, Benjamin Van Roy et al.2022 · 3 citationsarXiv
On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning2210.16877v1 · Dilip Arumugam, Mark K. Ho, Noah D. Goodman et al.2022 · 0 citationsarXiv
Is Stochastic Gradient Descent Near Optimal?2209.08627v2 · Yifan Zhu, Hong Jun Jeon, Benjamin Van Roy2022 · 0 citationsarXiv
Robustness of Epinets against Distributional Shifts2207.00137v1 · Xiuyuan Lu, Ian Osband, Seyed Mohammad Asghari et al.2022 · 1 citationarXiv
Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrapping2206.03633v1 · Vikranth Dwaracherla, Zheng Wen, Ian Osband et al.2022 · 6 citationsarXiv
Between Rate-Distortion Theory & Value Equivalence in Model-Based Reinforcement Learning2206.02025v1 · Dilip Arumugam, Benjamin Van Roy2022 · 0 citationsarXiv
Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning2206.02072v2 · Dilip Arumugam, Benjamin Van Roy2022 · 4 citationsarXiv
Non-Stationary Bandit Learning via Predictive Sampling2205.01970v9 · Yueyang Liu, Xu Kuang, Benjamin Van Roy2022 · 7 citationsarXiv
An Analysis of Ensemble Sampling2203.01303v2 · Chao Qin, Zheng Wen, Xiuyuan Lu et al.2022 · 3 citationsarXiv
An Information-Theoretic Framework for Supervised Learning2203.00246v6 · Hong Jun Jeon, Yifan Zhu, Benjamin Van Roy2022 · 1 citationarXiv
Evaluating High-Order Predictive Distributions in Deep Learning2202.13509v1 · Ian Osband, Zheng Wen, Seyed Mohammad Asghari et al.2022 · 1 citationarXiv
Gaussian Imagination in Bandit Learning2201.01902v3 · Yueyang Liu, Adithya M. Devraj, Benjamin Van Roy et al.2022 · 1 citationarXiv
The Value of Information When Deciding What to Learn2110.13973v1 · Dilip Arumugam, Benjamin Van Roy2021 · 4 citationsarXiv
The Neural Testbed: Evaluating Joint Predictions2110.04629v4 · Ian Osband, Zheng Wen, Seyed Mohammad Asghari et al.2021 · 2 citationsarXiv
Deep Exploration for Recommendation Systems2109.12509v4 · Zheqing Zhu, Benjamin Van Roy2021 · 5 citationsarXiv
From Predictions to Decisions: The Importance of Joint Predictive Distributions2107.09224v3 · Zheng Wen, Ian Osband, Chao Qin et al.2021 · 0 citationsarXiv
Career total: 262 works. 102 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.