Corey Lynch

Broadly-Exploring, Local-Policy Trees for Long-Horizon Task Planning

2020 · arXiv (Cornell University)

Long-horizon planning in realistic environments requires the ability to reason over sequential tasks in high-dimensional state spaces with complex dynamics. Classical motion planning algorithms, such as rapidly-exploring random trees, are capable of efficiently exploring large …

GoalsEye: Learning High Speed Precision Table Tennis on a Physical Robot

2022 · arXiv (Cornell University)

Learning goal conditioned control in the real world is a challenging open problem in robotics. Reinforcement learning systems have the potential to learn autonomously via trial-and-error, but in practice the costs of manual reward design, …