
Introduction to Reinforcement Learning Theory for IT Engineers
Anyone can carry out machine learning as long as they have data, thanks to various tools and libraries provided in recent several years. However, you cannot properly use the outputs of programs without knowing their meaning. It is necessary to understand the algorithms and theoretical bases of how the results were derived.
In this seminar, we are going to have a reading society of the book "Introduction to Reinforcement Learning Theory for IT Engineers" to study about theoretical bases of policy iteration, value iteration, Monte Carlo method, DQN, etc.