Articles by Benjamin Van Roy

Claim page

Benjamin Van Roy

Activity

Upvotes

Folders

Articles

Choice Between Partial Trajectories: Disentangling Goals from Beliefs

21 December 2024 by Henrik Marklund and Benjamin Van Roy

Machine Learning, Artificial Intelligence

Maintaining Plasticity in Continual Learning via Regenerative Regularization

24 October 2024 by Saurabh Kumar and others

Machine Learning, Artificial Intelligence

Aligning AI Agents via Information-Directed Sampling

18 October 2024 by Hong Jun Jeon and Benjamin Van Roy

Machine Learning, Artificial Intelligence

Non-Stationary Bandit Learning via Predictive Sampling

29 August 2024 by Yueyang Liu and others

Machine Learning

Information-Theoretic Foundations for Machine Learning

20 August 2024 by Hong Jun Jeon and Benjamin Van Roy at

Stanford University

Machine Learning, Artificial Intelligence

Posterior Sampling for Continuing Environments

11 August 2024 by Wanqiao Xu and others

Machine Learning

The Need for a Big World Simulator: A Scientific Challenge for Continual Learning

6 August 2024 by Saurabh Kumar and others

Machine Learning, Artificial Intelligence

Satisficing Exploration for Deep Reinforcement Learning

16 July 2024 by Darmindra Arumugam and others

Machine Learning, Artificial Intelligence

Exploration Unbound

16 July 2024 by Darmindra Arumugam and others

Machine Learning, Artificial Intelligence

Efficient Exploration for LLMs

4 June 2024 by Vikranth Dwaracherla and others at

Google

Machine Learning, Artificial Intelligence

Adaptive Crowdsourcing Via Self-Supervised Learning

2 February 2024 by Anmol Kagrecha and others

Machine Learning, Human-Computer Interaction

RLHF and IIA: Perverse Incentives

1 February 2024 by Wanqiao Xu and others at

Google

Machine Learning, Artificial Intelligence

An Information-Theoretic Analysis of In-Context Learning

28 January 2024 by Hong Jun Jeon and others at

Stanford University

Machine Learning, Information Theory

A Definition of Continual Reinforcement Learning

1 December 2023 by David Abel and others at

Google

Machine Learning, Artificial Intelligence

An Information-Theoretic Analysis of Compute-Optimal Neural Scaling Laws

18 October 2023 by Hong Jun Jeon and Benjamin Van Roy

Machine Learning

Non-Stationary Contextual Bandit Learning via Neural Predictive Ensemble Sampling

14 October 2023 by Zheqing Zhu and others

Machine Learning, Information Retrieval

Continual Learning as Computationally Constrained Reinforcement Learning

20 August 2023 by Saurabh Kumar and others

Machine Learning, Artificial Intelligence

Scalable Neural Contextual Bandit for Recommender Systems

19 August 2023 by Zheqing Zhu and Benjamin Van Roy

Information Retrieval, Artificial Intelligence

A Definition of Non-Stationary Bandits

28 July 2023 by Yueyang Liu and others

Machine Learning

On the Convergence of Bounded Agents

20 July 2023 by David Abel and others

Machine Learning, Artificial Intelligence

Deep Exploration for Recommendation Systems

24 May 2023 by Zheqing Zhu and Benjamin Van Roy

Information Retrieval, Artificial Intelligence

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

19 May 2023 by Wanqiao Xu and others

Computation and Language, Artificial Intelligence

Fine-Tuning Language Models via Epistemic Neural Networks

10 May 2023 by Ian Osband and others

Computation and Language, Artificial Intelligence

Bayesian Reinforcement Learning with Limited Cognitive Load

5 May 2023 by Darmindra Arumugam and others

Machine Learning, Artificial Intelligence

Inclusive Artificial Intelligence

3 March 2023 by Darmindra Arumugam and others

Machine Learning, Artificial Intelligence

An Analysis of Ensemble Sampling

1 March 2023 by Chao Qin and others

Machine Learning

Approximate Thompson Sampling via Epistemic Neural Networks

18 February 2023 by Ian Osband and others

Machine Learning, Artificial Intelligence

Leveraging Demonstrations to Improve Online Learning: Quality Matters

8 February 2023 by Botao Hao and others

Machine Learning, Statistics Theory

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

30 October 2022 by Darmindra Arumugam and others

Machine Learning, Artificial Intelligence

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

30 October 2022 by Darmindra Arumugam and Benjamin Van Roy

Machine Learning, Information Theory

This is an AI-generated summary

Key points

Topics

Machine Learning Artificial Intelligence Information Theory Optimization and Control Computation and Language Information Retrieval Systems and Control Statistics Theory Probability Methodology Human-Computer Interaction Computer Science and Game Theory Trading and Market Microstructure Networking and Internet Architecture