Picture for Alekh Agarwal

Alekh Agarwal

A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks

May 26, 2023
Jacob Abernethy, Alekh Agarwal, Teodor V. Marinov, Manfred K. Warmuth

Access Paper or Ask Questions

Leveraging User-Triggered Supervision in Contextual Bandits

Feb 07, 2023
Alekh Agarwal, Claudio Gentile, Teodor V. Marinov

Access Paper or Ask Questions

VO$Q$L: Towards Optimal Regret in Model-free RL with Nonlinear Function Approximation

Dec 12, 2022
Alekh Agarwal, Yujia Jin, Tong Zhang

Figure 1 for VO$Q$L: Towards Optimal Regret in Model-free RL with Nonlinear Function Approximation

Figure 2 for VO$Q$L: Towards Optimal Regret in Model-free RL with Nonlinear Function Approximation

Figure 3 for VO$Q$L: Towards Optimal Regret in Model-free RL with Nonlinear Function Approximation

Access Paper or Ask Questions

Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity

Jun 15, 2022
Alekh Agarwal, Tong Zhang

Access Paper or Ask Questions

Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling

Mar 15, 2022
Alekh Agarwal, Tong Zhang

Figure 1 for Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling

Access Paper or Ask Questions