This is in reference to the question asking us to compute the value of Q (5, left). I got an answer of 0.391 but the system is refusing to accept that as an answer stating it is the answer for Q (4, left) which it definitely is not. Can this problem be set right please?
Please post a screen capture image that shows the question you are discussing.
I have added a screenshot for your referral. Thanks for asking.
Thanks.
Can you show your steps for computing the reward value?
1 Like
0 + 0 * 0.25 + 0 * 0.25^2 + 0 * 0.25^3 + 100 * 0.25^4
= 100 * 0.25^4
= 0.390625
There should only be four steps.
- From 5 to 4 (that’s the given instruction).
- Then follow the optimum path arrows (from 4 to 5 to 6).
1 Like
OK, thanks. I got it.
This looks like three steps:
5 to 4
4 to 5
5 to 6
@dvvilkins, we were discussing(a year ago) how many steps were in the calculation, not the steps in the state diagram.
1 Like