AE 598 RL - Special Topics - Reinforcement Learning
Subject offerings of new and developing areas of knowledge in aerospace engineering intended to augment existing formal courses. Topics and prerequisites vary for each section. See Class Schedule or departmental course information for both. Course Information: May be repeated in the same or separate terms if topics vary to a maximum of 12 hours.
Title: Reinforcement Learning for Dynamics and Control Theory and practice of reinforcement learning as a tool for machine learning and artificial intelligence, applied to control, dynamics, and robotics, with a particular emphasis on computation. Topics will include reinforcement learning algorithms (temporal difference, Q-learning, policy gradient, actor-critic), function approximation and the use of deep neural networks, and efficient implementation on parallel architectures. Restrictions and prerequisites: CS 446 or equivalent; experience with TensorFlow, PyTorch, or equivalent.
Option 1Number of Required Visit(s): 0
Course Level: Graduate