隨機時序決策與分析
Sequential Decision Modeling and Analytics
| 節 | 週五 |
|---|---|
2 09:00–09:50 | 隨機時序決策與分析 MB506（光復） 3 節連堂 |
3 10:10–11:00 | |
4 11:10–12:00 |
* 根據陽明交大上課時間表所列
This course provides an in-depth exploration of sequential decision making and its industrial applications. Students will gain a solid foundation in stochastic modeling, Markov Decision Processes (MDPs), and Reinforcement Learning (RL), with a focus on practical applications in optimization, automation, and decision-making under uncertainty. Hands-on experience through project work and presentations will ensure students can apply these concepts to real-world industrial problems.
Basic probability theory, operations research
無備註
Python-language programming
•Homework Assignments: 10% •Midterm Exam: 30% •Project: 30% •Final Exam: 30%
Markov Decision Process (MDP)
1. Basic Concept of Markov Decision Process 2. Finite or infinite MDP 3. Policy and Value Iteration Method
- 講授：
- 15
Reinforcement Learning (RL)
1. Basic concept of RL 2. Model-Free RL 3. Deep RL 4. Multi-Armed Bandits
- 講授：
- 15
Preliminary
1. Probability Theory 2. Discrete Markov Chain 3. Sequential Decision-Making Framework
- 講授：
- 9
| 週次 | 主題 |
|---|---|
| 第 1 週 | Introduction to Sequential Decision Making and Analytics 2024-09-06(五) |
| 第 2 週 | Stochastic Modeling: Basic Probability, Conditional Probabilities 2024-09-13(五) |
| 第 3 週 | Stochastic Modeling: Markov Chain Properties 2024-09-20(五) |
| 第 4 週 | MDP: Overview of MDP 2024-09-27(五) |
| 第 5 週 | MDP: Policy and Value Functions 2024-10-04(五) |
| 第 6 週 | MDP: Bellman Equations 2024-10-11(五) |
| 第 7 週 | MDP: Finite-Horizon and Infinite-Horizon MDPs 2024-10-18(五) |
| 第 8 週 | MDP: Policy and Value Iteration Methods 2024-10-25(五) |
| 第 9 週 | Midterm Exam 2024-11-01(五) |
| 第 10 週 | RL: Introduction to Reinforcement Learning 2024-11-08(五) |
| 第 11 週 | RL: Q-Learning and SARSA 2024-11-15(五) |
| 第 12 週 | RL: Temporal Difference (TD) Learning 2024-11-22(五) |
| 第 13 週 | Multi-Armed Bandits: Basics and Exploration Strategies 2024-11-29(五) |
| 第 14 週 | Multi-Armed Bandits: Advanced Topics and Thompson sampling 2024-12-06(五) |
| 第 15 週 | Final Exam 2024-12-13(五) |
| 第 16 週 | Project Presentation 2024-12-20(五) |
• Ross, Sheldon M. (2014) Introduction to probability models. Academic press. (optional) • Puterman, M. L. (2014). Markov decision processes: discrete stochastic dynamic programming. John Wiley & Sons. (optional) • Sutton R. & Barto A. (2020). Reinforcement Learning: An Introduction (2nd Edition). Cambridge: The MIT Press. (free online)
- 地點
- MB512
- 時間
- Mon. 12:00 – 14:00 (or by appointment)
- 聯絡方式
- kaiwen.tien@nycu.edu.tw