Recent & Upcoming Talks

2024

A Tale of Two Algorithmic Principles: Optimism and Posterior Sampling.

The principle of optimism in the face of uncertainty and posterior sampling are algorithmic ideas that drive many no-regret algorithms …
Dec 10, 2024 12:00 AM Columbia University in the City of New York

Experiment Planning with Function Approximation.

We study the problem of experiment planning with function approximation in contextual bandit problems. In settings where there is a …
Apr 29, 2024 12:00 AM San Diego, Virtual, Brown University

The Dissimilarity Dimension: Sharper Bounds for Optimistic Algorithms.

The principle of Optimism in the Face of Uncertainty (OFU) is one of the foundational algorithmic design choices in Reinforcement …
Jan 10, 2024 12:00 AM MIT, UCSD, Virtual, Oaxaca

2023

RLHF: Reinforcement Learning with Once-per-Episode Feedback

Despite Reinforcement learning’s remarkable success in several application and simulation domains, research in the field has …
Feb 16, 2023 12:00 AM Virtual

LEARNING SYSTEMS IN ADAPTIVE ENVIRONMENTS. THEORY, ALGORITHMS AND DESIGN

February/March 2023
Feb 14, 2023 12:00 AM University of California Los Angeles, Cornell University, University College London, University of Chicago, Yale University, University of California San Diego, Brown University

2022

Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity.

Reinforcement learning provides an automated framework for learning behaviors from high-level reward specifications, but in practice …
Nov 1, 2022 12:00 AM Princeton University, University College London

On the Statistical Complexity of Batch Learning: Theory and Algorithms

In this work we develop the technique of optimism regularization, a simple way of inducing optimistic predictions in NN models. I show …
Nov 1, 2022 12:00 AM Oxford University