Deep Reinforcement Learning

1.5 credits · Graduate

Introduces fundamental concepts and essential algorithms of deep reinforcement learning, such as the basics of machine learning/deep learning, reinforcement learning, Markov decision process, dynamic programing, tabular methods, including Monte-Carlo and temporal difference, value-function approximation, policy gradient methods, and sample advanced algorithms, including deep Q-networks (DQN) and deep deterministic policy gradient (DDPG). Students are required to complete a project.