校際選修

115-1 選課時程

進行中

  • 初選第一階段 6/15/2026
  • 初選第二階段 6/22/2026
  • 校際選修 8/24/2026
  • 初選第三階段 8/31/2026
  • 開學後加退選 9/7/2026
  • 逾期加退選 9/21/2026
選課資源

強化學習原理(英文授課)

Reinforcement Learning

學期
109-2
學分
3 學分
當期課號
5269
永久課號
IOC5208
開課單位
資訊科學與工程研究所
授課教師
謝秉均
校區
光復
類別
選修
上課時間表
週二
週五
2
09:00–09:50
強化學習原理(英文授課)
EC115
5
13:20–14:10
強化學習原理(英文授課)
EC115
2 節連堂
6
14:20–15:10

* 根據陽明交大上課時間表所列

概述

- Learn how to model tasks as RL problems. - Understand RL from a theoretical viewpoint - Learn how to systematically solve RL problems by using various RL algorithms and perform analysis of these algorithms - Learn how to implement deep RL algorithms using software packages (e.g. Tensorflow and Pytorch) through team project

先修科目

- Some math maturity: Familiarity with calculus and probability (basic understanding of optimization would help ) - Programming language: python (familiarity with tensorflow/pytorch would help)

評分方式

Homework: 30% Theory Project: 30% Team Implementation Project: 40% (including 10% for presentation)

週次計畫
週次主題
第 1 週We will try our best to discuss all of the following topics: 1. Markov decision process (MDP) and planning in MDPs 2. Introduction to numerical optimization: line search and trust region methods 3. Model-free policy evaluation 4. Model-free control and stochastic approximation 5. Policy-gradient methods (REINFORCE, A2C, DPG) 6. Function approximation 7. Trust-region policy optimization: TRPO, PPO, and CPO 8. Deep value-based approach 9. Off-policy evaluation 10. Distributional RL 11. Multi-armed Bandits
教科書

Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, MIT Press, 2nd edition, 2018 Alekh Agarwal, Nan Jiang, and Sham M. Kakade, Reinforcement Learning: Theory and Algorithms, 2019 Nocedal, Jorge, and Stephen Wright. Numerical optimization. Springer Science & Business Media, 2006 Léon Bottou, Frank E. Curtis, and Jorge Nocedal, Optimization Methods for Large-Scale Machine Learning. arXiv 2016 Tor Lattimore and Csaba Szepesvari, Bandit Algorithms. 2019

Office Hours
地點
EC713
時間
By appointment
聯絡方式
By email: pinghsieh@nctu.edu.tw