You should take this course if you have an interest in machine learning and the desire to engage with it from a theoretical perspective. Through a combination of classic papers and more recent work, you will explore automated decision-making from a computer-science perspective. You will examine efficient algorithms, where they exist, for single-agent and multi-agent planning as well as approaches to learning near-optimal decisions from experience. At the end of the course, you will replicate a result from a published paper in reinforcement learning.
Why Take This Course? This course will prepare you to participate in the reinforcement learning research community. You will also have the opportunity to learn from two of the foremost experts in this field of research, Profs. Charles Isbell and Michael Littman.
* Reinforcement Learning Basics
* Introduction to BURLAP
* TD Lambda
* Convergence of Value and Policy Iteration
* Reward Shaping
* Partially Observable MDPs
* Topics in Game Theory
* Further Topics in RL Models
MOOCs stand for Massive Open Online Courses. These arefree online courses from universities around the world (eg. StanfordHarvardMIT) offered to anyone with an internet connection.
How do I register?
To register for a course, click on "Go to Class" button on the course page. This will take you to the providers website where you can register for the course.
How do these MOOCs or free online courses work?
MOOCs are designed for an online audience, teaching primarily through short (5-20 min.) pre recorded video lectures, that you watch on weekly schedule when convenient for you. They also have student discussion forums, homework/assignments, and online quizzes or exams.
Extremely slow paced, with most of the topics handwaved. I've read Sutton's book. Topics (not all) from the book were covered on a shallow level. Additional topics were explained in such a way that you need to read other resources in order to actually implement them.
There are better books and resources on RL, don't waste time on this course
Vinayak Mehtaaudited this course, spending 10 hours a week on it and found the course difficulty to be hard.
The way in which the instructors teach is awesome.
This is a masters level machine learning course. I would recommend taking this course at a slow pace if you're a beginner in the machine learning domain, making sure that you get a thorough understanding of the material.
Jason Wu is taking this course right now, spending 8 hours a week on it and found the course difficulty to be medium.
One of the best course. I have learned since their machine learning course and love the interaction between the lecturer. Some people complained about the slow pace, but there is actually a simplify version of RL in the ML class I've mentioned. Go check it out if you don't have time. This course supposed to go "deep". And believe me, the RL course you might take in the college or grad school is much more "slow paced" than this one.
- They let student to think along the way, not just cram the stuffs into our head
- A sense of humor in teaching the class
- Lack of support on the homework, as well as using framework BURLAP require steep learning curve
- Some context such as TD(0) and TD(1) can be explained more intuitively (maybe it's just me not quite understand that part)
I am not assessing the whole course cause I couldn't make it through the first week because I didn't like it very much. The pace is very slow and the course doesn't seem to be very thorough. There is lots of redundant chit-chat, analogies and talking that doesn't contribute to better understanding. It's also quite chaotic and unsystematic. Maybe it's a good idea for people that are not very bright and have no knowledge whatsoever on the topic, but otherwise I wouldn't recommend it. (As I mentioned my opinion is based solely on the first chapter - MDPs)