https://www.coursera.org/learn/fundamentals-of-reinforcement-learning/home/welcome

• Text book:

  • http://incompleteideas.net/book/the-book-2nd.html
  • Book reference solutions: ‣

• 赵世钰老師的 RL 課程和課本: 强化学习的数学原理

  • https://github.com/MathFoundationRL/Book-Mathematical-Foundation-of-Reinforcement-Learning
  • https://www.youtube.com/watch?v=TGIBuBd-V6I&list=PLEhdbSEZZbDYwsXT1NeBZbmPCbIIqlgLS
  • Roadmap

<aside> 💡

赵世钰老師的 RL 從數學的角度透徹理解, 這種從根部底層的理解讓人通體舒暢!

個人更偏好這樣學習, 因此這裡筆記 Coursera 這門課的時候如果講的不清楚, 會從赵世钰老師的 RL 的角度來筆記

</aside>

• The goal of this course:

  Fundamentals of Reinforcement Learning_ Learning Objectives .pdf

• Course Quiz and Assignment:

  Ref solution by others: https://github.com/ChanchalKumarMaji/Reinforcement-Learning-Specialization

Week 1: An Introduction to Sequential Decision-Making

Week 2: Introduction to Markov Decision Processes

Week 3: Value Functions & Bellman Equations

Week 4: Dynamic Programming (Value and Policy Iteration)

• Study Plan (Delete after finished)