強化學習
Reinforcement Learning
| 節 | 週三 |
|---|---|
5 13:20–14:10 | 強化學習 CM215（歸仁） 3 節連堂 |
6 14:20–15:10 | |
7 15:30–16:20 |
* 根據陽明交大上課時間表所列
This course provides a clear and simple account of the key ideas and algorithms of reinforcement learning and takes the point of view of artificial intelligence and engineering. We also survey some of the frontiers of reinforcement learning in biology and applications.
Python
無備註
教師未提供此項資料
In-class projects (60%) Final project (40%)
The Reinforcement Learning Problem
The Reinforcement Learning Problem Introduction
- 講授：
- 6
Tabular Solution Methods Introduction
Multi-arm Bandits Finite Markov Decision Processes Dynamic Programming Monte Carlo Methods Temporal-Difference Learning Eligibility Traces Planning and Learning with Tabular Methods
- 講授：
- 10
- 實作：
- 8
Approximate Solution Methods Introduction
On-policy Approximation of Action Values Off-policy Approximation of Action Values Policy Approximation
- 講授：
- 8
- 實作：
- 4
Frontiers
Psychology Neuroscience Applications and Case Studies
- 講授：
- 8
- 實作：
- 4
| 週次 | 主題 |
|---|---|
| 第 1 週 | The Reinforcement Learning Problem 2026-02-25(三) |
| 第 2 週 | Tabular Solution Methods Introduction 2026-03-04(三) |
| 第 3 週 | Multi-arm Bandits 2026-03-11(三) |
| 第 4 週 | Finite Markov Decision Processes 2026-03-18(三) |
| 第 5 週 | Dynamic Programming 2026-03-25(三) |
| 第 6 週 | Monte Carlo Methods 2026-04-01(三) |
| 第 7 週 | Temporal-Difference Learning 2026-04-08(三) |
| 第 8 週 | Eligibility Traces 2026-04-15(三) |
| 第 9 週 | Planning and Learning with Tabular Methods Introduction 2026-04-22(三) |
| 第 10 週 | Approximate Solution Methods Introduction 2026-04-29(三) |
| 第 11 週 | On-policy Approximation of Action Values 2026-05-06(三) |
| 第 12 週 | Off-policy Approximation of Action Values 2026-05-13(三) |
| 第 13 週 | Policy Approximation 2026-05-20(三) |
| 第 14 週 | Psychology 2026-05-27(三) |
| 第 15 週 | Neuroscience 2026-06-03(三) |
| 第 16 週 | Final Project Presentation 2026-06-10(三) |
教師未提供此項資料
- 地點
- Go far 209
- 時間
- 10:00~12:00, Wed.
- 聯絡方式
- 03-5731350