It's UWAweek 51

help3011

This forum is provided to promote discussion amongst students enrolled in CITS3011 Intelligent Agents.

Please consider offering answers and suggestions to help other students! And if you fix a problem by following a suggestion here, it would be great if other interested students could see a short "Great, fixed it!"  followup message.

How do I ask a good question?
Displaying selected article
Showing 1 of 83 articles.
Currently 1 other person reading this forum.


 UWA week 44 (2nd semester, 1st exam week) ↓
SVG not supported

Login to reply

👍?
helpful
6:35pm Fri 1st Nov, Andrew G.

ANONYMOUS wrote:
> so in an unknown environment, which one should be used? > Q-learning can just learn state-action pairs, but utility learning can just learn the transition model then use it to calculate state utilities. I'm having difficulty finding pros and cons of using one over the other (other than computation).
There is not a clear answer, since as I say: In a system with no known model where we are not able to assume anything about the structure of the system, they become basically equivalent. This information is covered in the lectures. In general you are expected to have a sufficient understanding of the logic and properties of these techniques that you should be able to assess a novel situation and determine for yourself the merits or disadvantages to each approach (or, indeed, when they are basically equivalent).

The University of Western Australia

Computer Science and Software Engineering

CRICOS Code: 00126G
Written by [email protected]
Powered by history
Feedback always welcome - it makes our software better!
Last modified  8:08AM Aug 25 2024
Privacy policy