193 results on '"Benjamin Van Roy"'
Search Results
2. An Information-Theoretic Analysis of In-Context Learning.
3. Efficient Exploration for LLMs.
4. Nonstationary Bandit Learning via Predictive Sampling.
5. Scalable Neural Contextual Bandit for Recommender Systems.
6. Deep Exploration for Recommendation Systems.
7. Approximate Thompson Sampling via Epistemic Neural Networks.
8. Leveraging Demonstrations to Improve Online Learning: Quality Matters.
9. Choice between Partial Trajectories.
10. Aligning AI Agents via Information-Directed Sampling.
11. The Need for a Big World Simulator: A Scientific Challenge for Continual Learning.
12. Satisficing Exploration for Deep Reinforcement Learning.
13. Information-Theoretic Foundations for Neural Scaling Laws.
14. Information-Theoretic Foundations for Machine Learning.
15. Exploration Unbound.
16. An Information-Theoretic Analysis of In-Context Learning.
17. Efficient Exploration for LLMs.
18. Adaptive Crowdsourcing Via Self-Supervised Learning.
19. Reinforcement Learning, Bit by Bit.
20. Evaluating high-order predictive distributions in deep learning.
21. Epistemic Neural Networks.
22. A Definition of Continual Reinforcement Learning.
23. Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent States.
24. Satisficing in Time-Sensitive Bandit Learning.
25. Bayesian Reinforcement Learning with Limited Cognitive Load.
26. Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models.
27. Scalable Neural Contextual Bandit for Recommender Systems.
28. Leveraging Demonstrations to Improve Online Learning: Quality Matters.
29. Continual Learning as Computationally Constrained Reinforcement Learning.
30. Maintaining Plasticity via Regenerative Regularization.
31. A Definition of Continual Reinforcement Learning.
32. A Definition of Non-Stationary Bandits.
33. On the Convergence of Bounded Agents.
34. Non-Stationary Contextual Bandit Learning via Neural Predictive Ensemble Sampling.
35. Approximate Thompson Sampling via Epistemic Neural Networks.
36. RLHF and IIA: Perverse Incentives.
37. Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrapping.
38. The Value of Information When Deciding What to Learn.
39. Deciding What to Learn: A Rate-Distortion Approach.
40. An Information-Theoretic Framework for Deep Learning.
41. The Neural Testbed: Evaluating Joint Predictions.
42. An Analysis of Ensemble Sampling.
43. Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning.
44. An Information-Theoretic Analysis of Compute-Optimal Neural Scaling Laws.
45. Fine-Tuning Language Models via Epistemic Neural Networks.
46. Posterior Sampling for Continuing Environments.
47. Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning.
48. Between Rate-Distortion Theory & Value Equivalence in Model-Based Reinforcement Learning.
49. On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning.
50. Gaussian Imagination in Bandit Learning.
Catalog
Books, media, physical & digital resources
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.