Open
Description
In the third line of the "strategy" function:
def strategy(observation):
score, dealer_score, usable_ace = observation
# Stick (action 0) if the score is > 20, hit (action 1) otherwise
return 0 if score >= 20 else 1
"> 20" should be ">= 20"
Also, the same typo in the "sample_policy" function, in the "MC Prediction.ipynb" file.
Thank you for your hard work!
Metadata
Metadata
Assignees
Labels
No labels