● 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 would cover several basic ideas of RL and its 
<br>applications to system designs. 
<br>
<br>● 參考書籍(References)
<br># Richard S. Sutton and Andrew G. Barto, Reinforcement learning: an 
<br>Introduction,  2nd edition.
<br># C.-T. Chen, Linear System Theory and Design, 4th edition. 
<br>
<br>● 教學方式(Teaching Method)
<br>Blackboard and PowerPoint presentation.
<br>
<br>● 教學進度(Syllabus)
<br>Ch1 fr<x>amework of Reinforcement Learning 
<br>Ch2 Dynamic programming 
<br>Ch3 Monte Carlo methods 
<br>Ch4 Sarsa and Q-learning 
<br>Ch5 n-step Sarsa
<br>Ch6 Function Approximation methods
<br>Ch7 Planning and learning
<br>Ch8 Eligibility traces and learning
<br>Ch9 Policy gradient methods
<br>
<br>● 成績考核(Evaluation)
<br>HW: 20% 
<br>Exams: 20% x 4=80%