查詢教學大綱與進度

教學大綱與進度

課程基本資料：

學年期課號課程名稱階段學分時數修教師班級人撤備註

108-2 274053 深度強化學習 1 3.0 3 ★ 賴冠廷電子四甲
電子四乙 15 1 電子四甲乙和電子所合開,限25人

學年期	課號	課程名稱	階段	學分	時數	修	教師	班級	人	撤	備註
108-2	274053	深度強化學習	1	3.0	3	★	賴冠廷	電子四甲電子四乙	15	1	電子四甲乙和電子所合開,限25人

教學大綱與進度：

教師姓名賴冠廷

Email ktlai@ntut.edu.tw

最後更新時間 2020-02-15 16:51:58

課程大綱 The goal of this course is to introduce fundamental theories behind deep reinforcement learning and summarize the state-of-the-art research results. We will also teach how to use Python deep learning framework (TensorFlow & PyTorch) and demonstrate how to train software agents to learn different tasks. The content includes: 1.Introduction to Reinforcement Learning 2. Finite Markov Decision Processes 3.Tabular Learning and Dynamic Programming 4.Monte Carlo Methods 5.Temporal-Difference Learning 6.Deep Q-Networks (DQN) 7.Actor-Critic Methods (A3C & A2C) 8.Trust Regions – TRPO, PPO and ACKTR

課程進度 1.Introduction to Reinforcement Learning 2. Tabular Learning and Multi-armed Bandits 2.Finite Markov Decision Processes 4. Dynamic Programming 5.Monte Carlo Methods 6.Temporal-Difference Learning 7. Approximation Methods 8. Deep Q-Networks (DQN) 9. OpenAI Gym 10.Actor-Critic Methods (A3C & A2C) 11.Trust Regions – TRPO, PPO and ACKTR 12. Stocks Trading using RL 13. Chatbots Training with RL 14. AlphaGoZero 15. RL in Virtual Reality 16. Microsoft AirSim

評量方式與標準 Homework (70%) Final Project (30%)

使用教材、參考書目或其他 【遵守智慧財產權觀念，請使用正版教科書，不得使用非法影印教科書】

使用外文原文書：是
1. Maxim Lapan, "Deep Reinforcement Learning Hands-On", Packt Publishing, 2018 (ISBN-13: 978-1788834247) 2. Richard S. Sutton and Andrew G. Barto, "Reinforcement Learning: An Introduction," A Bradford Book, 2018 (ISBN-13: 978-0262039246)

課程諮詢管道

備註

教師姓名	賴冠廷
Email	ktlai@ntut.edu.tw
最後更新時間	2020-02-15 16:51:58
課程大綱	The goal of this course is to introduce fundamental theories behind deep reinforcement learning and summarize the state-of-the-art research results. We will also teach how to use Python deep learning framework (TensorFlow & PyTorch) and demonstrate how to train software agents to learn different tasks. The content includes: 1.Introduction to Reinforcement Learning 2. Finite Markov Decision Processes 3.Tabular Learning and Dynamic Programming 4.Monte Carlo Methods 5.Temporal-Difference Learning 6.Deep Q-Networks (DQN) 7.Actor-Critic Methods (A3C & A2C) 8.Trust Regions – TRPO, PPO and ACKTR
課程進度	1.Introduction to Reinforcement Learning 2. Tabular Learning and Multi-armed Bandits 2.Finite Markov Decision Processes 4. Dynamic Programming 5.Monte Carlo Methods 6.Temporal-Difference Learning 7. Approximation Methods 8. Deep Q-Networks (DQN) 9. OpenAI Gym 10.Actor-Critic Methods (A3C & A2C) 11.Trust Regions – TRPO, PPO and ACKTR 12. Stocks Trading using RL 13. Chatbots Training with RL 14. AlphaGoZero 15. RL in Virtual Reality 16. Microsoft AirSim
評量方式與標準	Homework (70%) Final Project (30%)
使用教材、參考書目或其他	【遵守智慧財產權觀念，請使用正版教科書，不得使用非法影印教科書】使用外文原文書：是 1. Maxim Lapan, "Deep Reinforcement Learning Hands-On", Packt Publishing, 2018 (ISBN-13: 978-1788834247) 2. Richard S. Sutton and Andrew G. Barto, "Reinforcement Learning: An Introduction," A Bradford Book, 2018 (ISBN-13: 978-0262039246)
課程諮詢管道
備註