Reinforcement learning and planning for preference balancing tasks
Aleksandra Faust · AI Matters · 2015
Many robotic motion tasks, such as UAV control, have non-linear and high-dimensional dynamics. Difficult for both human demonstration and explicit solutions, these tasks can be described with opposing preferences. This thesis develops PEARL, a real-time solution for such tasks on acceleration-controlled systems with unknown dynamics, and finds PEARL's safety conditions.