 |
Reinforcement Learning and
Artificial
Intelligence (RLAI)
|
Function
Approximation Assignments
|
These may be assigned this year.
For this assigment you can think of the domain to be a 100 x 100 real
value coordinate system. You may realize that the dimensions
don't matter - but having a fixed size may make it easier to imagine
for now.
Take tile coder and run on the following data:
Training Data Points:
X Coordinate
|
Y
Coordinate
|
Value
|
30.0
|
10.0
|
5.0
|
70.0
|
20.0
|
3.0
|
8.0
|
50.0
|
-1.0
|
Test (Query) Data Points:
X
Coordinate
|
Y
Coordinate
|
Value
|
55.8
|
45.2
|
?
|
37.5
|
99.0
|
?
|
30.5
|
9.5
|
?
|
30.5
|
15
|
?
|
Use 16 tilings over the XY space and examine what happens when you
change the width of the tiles and alpha. To start, use a width of 10 (one tenth of the 100 x 100 space) and alpha = .1
You can download the tile coding software from:
http://rlai.cs.ualberta.ca/RLAI/RLtoolkit/RLtoolkit1.0.html#downloads
We will also be posting a more minimal download that is just the tile
coding software in the next couple of days.
Tile
coding software only
Tile
coding software documentation
Handin:
RELEVANT portions of your code. Do not hand in the RL code that
you downloaded, PLEASE.
Your results for various widths and alphas. Talk about your
results a bit. It would be nice (but not necessary) for you to
include some sort of 3d view (with Excel or similar) of what the
function looks like after training. Basically, do the assignment,
see what you find interesting, and briefly present it.
