Abstract: For many years machine learning solutions have been integrated into planning and control solutions. Contrary to traditional planning, integrated learning and planning offers the promise of new solutions that generalize to previously unseen scenarios, enhanced robustness to noise, and/or performance that was previously unachievable. However, despite these advancements, planning and learning are often kept separate, employed in a series of handoffs.
In this talk, we will discuss the difficulties and successes in coupling planning with learning. The solutions cover a wide variety of scenarios from end-to-end, to long-range planning, to multi-agent coordination. However, the challenges are fundamental. How is safety guaranteed or considered? Do solutions generalize? Is the solution interpretable?
Bio: Lydia Tapia is an Associate Professor in the Department of Computer Science at the University of New Mexico. She received her Ph.D. in Computer Science from Texas A&M University and her B.S. in Computer Science from Tulane University. Her research contributions are focused on the development of computationally efficient algorithms for the simulation and analysis of high-dimensional motions for robots and molecules. Specifically, she explores problems in computational structural biology, motion under stochastic uncertainty, and reinforcement learning. Lydia is the recipient of the 2016 Denice Denton Emerging Leader ABIE Award from the Anita Borg Institute, a 2016 NSF CAREER Award for her work on simulating molecular assembly, and the 2017 Computing Research Association Committee on the Status of Women in Computing Research (CRA-W) Borg Early Career Award.