CS 443
All notes are based on the course at UIUC CS 443 taught by professor Nan Jiang (姜楠).
As a senior Computer Science student embarking on the CS 443 course on Reinforcement Learning, I am filled with a sense of purpose and enthusiasm. This course, guided by Professor Nam Jiang, represents not just a pivotal point in my academic journey but also an opportunity to create a valuable resource for future students who will navigate the complexities of this advanced field. My decision to take this course in the upcoming semester is driven by a fascination with the dynamic and impactful world of RL. I understand the challenges that lie ahead, having encountered rigorous coursework in my academic path, but my commitment to delving deeper into Reinforcement Learning is unwavering. I am motivated not only by my desire to expand my own understanding but also by the prospect of aiding others in comprehending and appreciating the intricacies of this cutting-edge area of computer science.
Mathematics
Some notes on mahtematics see HERE!
Gymnasium
Some notes on a RL environment see HERE!
The Plan
- Introduction
- Markov Decision Process formulation
- Value function
- Bellman equation
- Optimality
- Value Iteration
- Learning setting
- Value prediction
- Function approximation
Instead of trying to produce a programme to simulate the adult mind, why not rather try to produce one which simulates the child’s? If this were then subjected to an appropriate course of education one would obtain the adult brain.
— Alan Turing
— John von Neumann