Normalisation and Final Score computation for the RL Project

RL Project 2021-56807e
#1

Hi,

The final scores will be computed by adding the scores of each of the 5 environments after normalising these between 0-1.

For the Acrobot and the Taxi environment, min-max normalisation will be used.
For the KBC problems, min-max normalisation after applying a log operator will be used.
The scores will be computed after the submission period has ended.

Thanks,
Siddhartha.

#2

Hi. How can we select out best submission to be considered for the grading?
This is crucial given that the leaderboard only updates on the basis of acrobot problem.

#3

Hi, pick your submission here.

Please note, that the leaderboard with the selected submission will update later.

1 Like
Submission Selection for Leaderboard
#4

Thanks, @vrv, This was much needed.

#5

What would be the base of the log operator that would be applied to our kbc scores?

#6

@siddhartha Just a clarification each environment carries a weightage of 1 or all kbc environments combined carry a weightage of 1

#7

Each of the kbc assignments will be normalised to 1.

#8

Hi, base of the log operator will be 2.

#9

Should It matter the base of the log, i guess it will cancel in numerator and denominator?

1 Like