● 課程說明(Course Desc<x>ription)
<br>Machine learning has been proved useful for addressing a number of engineering
<br>problems. Among various advanced machine learning methods, reinforcement
<br>learning (RL) has attracted much attention because of its effectiveness and
<br>simplicity. This course covers some basic ideas of RL and has the primary focus on 
<br>the software implementation of RL algorithms.  
<br>
<br>● 建議先修課程(Suggested Prerequisites)
<br>Linear Algebra, Probability, and Calculus. 
<br>
<br>● 參考書籍(References)
<br># Enes Bilgin, Mastering Reinforcement Learning with Python
<br># Richard S. Sutton and Andrew G. Barto, Reinforcement learning: an Introduction, 
<br>2nd 
<br>edition.
<br># 強化學習導論，邱偉育 (紙本:全華圖書出版；電子書:Pubu)
<br>
<br>
<br>● 教學方式(Teaching Method)
<br>Blackboard, PowerPoint, and videos.
<br>
<br>● 教學進度(Syllabus)
<br>fr<x>amework of Reinforcement Learning
<br>Tutorial on Python
<br>Gridworld problems
<br>Monte Carlo methods
<br>Sarsa and Q-learning
<br>n-step Sarsa
<br>Mountain car problems
<br>Function Approximation methods
<br>Planning and learning
<br>Policy gradient methods
<br>
<br>● 成績考核(Evaluation)
<br>Exams: 25% x 4=100%