Quick Questions for April 7, 2020

JavaScript isn't enabled in your browser, so this file can't be opened. Enable and reload.

These questions are answered within the lecture video and can be answered in about 1 sentence each. We are hoping these help you stay on track watching lecture and make sure you're processing the content! Please complete by Tuesday at midnight, Eastern time.

MIT Kerberos (part in email before @mit.edu)

Which arrows/direct relationships exist in a Markov decision process?

A state to the subsequent state?

An action to the subsequent action?

A reward to the subsequent reward?

An action to the subsequent state?

What is an example of a reward in a medical setting?

Why may we want to approximate Q(s, a) with a function instead of using a table?

What makes RL in the medical setting so different from recent RL successes? What do we have to be careful of?

Why would we want to use a summary function to represent state? How is it often learned?

Submit

Clear form

Never submit passwords through Google Forms.

This content is neither created nor endorsed by Google. Report Abuse - Terms of Service - Privacy Policy

Forms