Dylan P. Losey

Asking Easy Questions: A User-Friendly Approach to Active Reward Learning

2019 · arXiv (Cornell University)

Robots can learn the right reward function by querying a human expert. Existing approaches attempt to choose questions where the robot is most uncertain about the human's response; however, they do not consider how easy …

Waypoint-Based Reinforcement Learning for Robot Manipulation Tasks

2024 · arXiv (Cornell University)

Robot arms should be able to learn new tasks. One framework here is reinforcement learning, where the robot is given a reward function that encodes the task, and the robot autonomously learns actions to maximize …