59 results on '"J. Foster"'
Search Results
2. Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization.
3. Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF.
4. Online Estimation via Offline Estimation: An Information-Theoretic Framework.
5. The Power of Resets in Online Reinforcement Learning.
6. Harnessing Density Ratios for Online Reinforcement Learning.
7. Rich-Observation Reinforcement Learning with Continuous Latent Dynamics.
8. Scalable Online Exploration via Coverability.
9. Can large language models explore in-context?
10. Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression.
11. Foundations of Reinforcement Learning and Interactive Decision Making.
12. On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring.
13. Instance-Optimality in Interactive Decision Making: Toward a Non-Asymptotic Theory.
14. Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient.
15. Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games.
16. Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL.
17. Efficient Model-Free Exploration in Low-Rank MDPs.
18. A Note on Model-Free Reinforcement Learning with the Decision-Estimation Coefficient.
19. Efficient Contextual Bandits with Knapsacks via Regression.
20. Interaction-Grounded Learning with Action-inclusive Feedback.
21. Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information.
22. On the Complexity of Adversarial Decision Making.
23. Contextual Bandits with Large Action Spaces: Made Practical.
24. The Role of Coverage in Online Reinforcement Learning.
25. Guaranteed Discovery of Controllable Latent States with Multi-Step Inverse Models.
26. Independent Policy Gradient Methods for Competitive Reinforcement Learning.
27. The Statistical Complexity of Interactive Decision Making.
28. Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation.
29. Eluder Dimension and Generalized Rank.
30. Adapting to Misspecification in Contextual Bandits.
31. Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination.
32. Learning the Linear Quadratic Regulator from Nonlinear Observations.
33. Logarithmic Regret for Adversarial Online Control.
34. Improved Bounds on Minimax Regret under Logarithmic Loss via Self-Concordance.
35. Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations.
36. Open Problem: Model Selection for Contextual Bandits.
37. Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective.
38. Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles.
39. Naive Exploration is Optimal for Online LQR.
40. Learning nonlinear dynamical systems from a single trajectory.
41. Lower Bounds for Non-Convex Stochastic Optimization.
42. Hypothesis Set Stability and Generalization.
43. 𝓁∞ Vector Contraction for Rademacher Complexity.
44. Orthogonal Statistical Learning.
45. Sum-of-squares meets square loss: Fast rates for agnostic tensor completion.
46. The Complexity of Making the Gradient Small in Stochastic Convex Optimization.
47. Distributed Learning with Sublinear Communication.
48. Model selection for contextual bandits.
49. Practical Contextual Bandits with Regression Oracles.
50. Online Learning: Sufficient Statistics and the Burkholder Method.
Catalog
Books, media, physical & digital resources
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.