Tues Apr 09 Reading Questions
Please respond to these questions by Tues Apr 09 noon at the latest about Lecture 16 reading
We greatly appreciate short answers: phrases and incomplete sentences are okay! We are not expecting you to spend a long time on this; the goal is to check that you've read the articles and to raise discussion points that we will go over in class. If you submit multiple times, we will grade the most recent response before the deadline.
MIT email (e.g.
The authors seek to model mechanical ventilation in the ICU as a off-policy reinforcement learning algorithm. What is the action space? What is the reward space? (Short answers okay!)
What is the main difference between on-policy and off-policy reinforcement learning? (can be short!) Why do the authors choose to use off-policy learning here?
Figure 6 shows the learned feature importance. Pick one value and explain whether or not it makes sense to be a high/low weight.
Never submit passwords through Google Forms.
This content is neither created nor endorsed by Google.
Terms of Service