UROP Project

Safety in reinforcement learning

As artificial intelligence grows in prevalence and influence in our everyday lives, increasing effort goes towards guaranteeing safety of the learned behavior. We have recently developed a framework to ensure and quantify safety in the context of reinforcement learning (RL). We are looking for a UROP student researcher to design, implement, and conduct learning experiments, both in simulation and on hardware. The results will enable us to understand the interactions between our method and state-of-the-art deep RL algorithms.

Task

The UROP student researcher will be asked to do the following, with the help of the supervisor:  (1) read the current project paper(s) and a small amount of background material on the theoretical framework for the project,  (2) perform learning experiments in simulation, (3) perform learning experiments on hardware available in our lab, (4) present the final work at the end of the program.

Requirements

- Engineering, computer science, and/or mathematics educational background - Comfortable programming in Python - Interest in machine learning (artificial neural networks, reinforcement learning) - Highly motivated, problem-solving skills - Able to work independently (with supervisor support)