PhD Defense: Towards Robust and Adaptive Real-World Reinforcement Learning

The past decade has witnessed a rapid development of reinforcement learning (RL) techniques. However, there is still a gap between employing RL in simulators and applying RL models to challenging and diverse real-world systems. On the one hand, existing RL approaches have been shown to be fragile under perturbations in the environment, making it risky to deploy RL models in real-world applications where unexpected noise and interference exist. On the other hand, most RL methods focus on learning a policy in a fixed environment, and need to re-train a policy if the environment gets changed. For real-world environments whose specifications and dynamics can be ever-changing, these methods become less practical as they require a large amount of data and computations to adapt to a changed environment.This talk focuses on the above two challenges, and introduces a series of solutions to improve the robustness and adaptability of RL methods. For robustness, the proposed approaches explore the vulnerability of RL agents in multiple scenarios, and achieve state-of-the-art performance on robustifying RL policies. For adaptability, the proposed transfer learning and pretraining frameworks address challenging multi-task learning problems where tasks specifications can be drastically different.

Examining Committee

Chair:

Dr. Furong Huang

Dean's Representative:

Dr. Min Wu

Members:

Dr. Hal Daumé

Dr. Dinesh Manocha
Dr. Tom Goldstein
Dr. Kaiqing Zhang