Recent Forum Posts
 From categories: All categories News: Course News Discussions: General Discussions: HW0 Discussions: HW1 Discussions: HW2 Discussions: HW3 Discussions: HW4 Discussions: HW5 Discussions: Past Exams
page 1123...next »
07 Jul 2018 12:16
in discussion Discussions / General » mistake in the exam (moed A)

Thanks, it was fixed.

Re: mistake in the exam (moed A) by , 07 Jul 2018 12:16
jfqlr (guest) 06 Jul 2018 15:29
in discussion Discussions / General » mistake in the exam (moed A)

In Q1, last section it should be gamma squared in the denominator.

mistake in the exam (moed A) by jfqlr (guest), 06 Jul 2018 15:29
Tomer Ben Moshe (guest) 04 Jul 2018 05:08
in discussion Discussions / General » Question about recitation 9

I still don't understand the first equation.. What formula did you use? because
\phi(a|s;\theta)=P_t*a+(1-a)(1-P_t)

so

log(\phi(a|s;\theta))=log (P_t*a+(1-a)(1-P_t))

and you can't open that expession

by Tomer Ben Moshe (guest), 04 Jul 2018 05:08
03 Jul 2018 15:51
in discussion Discussions / General » recitation 11

Guy is right. The original text was correct (it wasn't a typo).
The following formula:

(1)
\begin{align} V_{t+1}^*(b) =& \max_a [r(b,a)+\gamma\sum_o V_t^*(T(b,a,o))] \end{align}

Can be written as the following 3 lines:

(2)
\begin{align} V_{t+1}^*(b)=&\max_a V_{t}^a(b) \\ V_{t}^a(b)=&\sum_o V^{a,o}_{t}(b) \\ V^{a,o}_{t}(b)=&\frac{r(b,a)}{|O|}+\gamma\Pr[o|b,a]V_t(T(b,a,o)) \end{align}
by , 03 Jul 2018 15:51
Guy (guest) 03 Jul 2018 13:36
in discussion Discussions / General » recitation 11

Why is this a mistake?
It appears also in the lecture in slide 30.
It seems as a different notation for the formula in the first row.

by Guy (guest), 03 Jul 2018 13:36
Tomer Ben Moshe (guest) 03 Jul 2018 13:35
in discussion Discussions / General » Question about recitation 9

Did you upload that? Because it still looks the same.

by Tomer Ben Moshe (guest), 03 Jul 2018 13:35
Tomer Ben Moshe (guest) 03 Jul 2018 13:33
in discussion Discussions / General » Recitation 7 and 8

So you need to change the description of that in the question in recitation 7 because it says the gamma is 0.5

by Tomer Ben Moshe (guest), 03 Jul 2018 13:33
03 Jul 2018 13:27
in discussion Discussions / General » Recitation 7 and 8

Recitation 7 solves the question with $\gamma=1$, while recitation 8 solves the question with $\gamma=0.5$.

Re: Recitation 7 and 8 by , 03 Jul 2018 13:27
03 Jul 2018 13:21
in discussion Discussions / General » recitation 11

thanks, the typo was fixed.

Re: recitation 11 by , 03 Jul 2018 13:21
03 Jul 2018 13:13
in discussion Discussions / General » Question about recitation 9

Thanks for pointing out the error - the scribe was fixed and clarified.

Re: Question about recitation 9 by , 03 Jul 2018 13:13
Tomer Ben Moshe (guest) 03 Jul 2018 13:13
in discussion Discussions / General » recitation 11

recitation 11 page 2 down.

3 lines before the end there is

V*_(t+1)=max_a (V*_t (V^a_t(b))

Isn't it supposed to be

V*_(t)=max_a (V*_t (V^a_t(b))?

recitation 11 by Tomer Ben Moshe (guest), 03 Jul 2018 13:13
Tomer Ben Moshe (guest) 03 Jul 2018 12:20
in discussion Discussions / General » Question about recitation 9

Hello,

In recitation 9 page 4 the last line I don't understand not the first equation and not the second equation.

If I understand correctly \phi(a|s;\theta)=P_t*a+(1-a)(1-P_t)

So how did it get to the first equation?

And for the second equation why did \nabla_\theta(P_t)=-x(s)?

Question about recitation 9 by Tomer Ben Moshe (guest), 03 Jul 2018 12:20
03 Jul 2018 12:01
in discussion Discussions / General » Random Walk

YES, you are right.

by , 03 Jul 2018 12:01
03 Jul 2018 11:54
in discussion Discussions / General » td lambda backward in ex. 7

1. Yes, you can say that
2. Thank you for finding this typos.

by , 03 Jul 2018 11:54
Tomer Ben Moshe (guest) 03 Jul 2018 10:23
in discussion Discussions / General » Recitation 7 and 8

Does recitation 7 end with the same exercise that recitation 8 begins?

Why does the answers to the TD-lambda are different?

Recitation 7 and 8 by Tomer Ben Moshe (guest), 03 Jul 2018 10:23
Tomer Ben Moshe (guest) 03 Jul 2018 06:22
in discussion Discussions / General » Random Walk

Did you mean
"If we move right to X=2, we need to first return to X=1, which takes E[T], and then return to X=0, which is another E[T]."

because I don't understand the meaning of what you wrote.

by Tomer Ben Moshe (guest), 03 Jul 2018 06:22
anon (guest) 03 Jul 2018 06:09
in discussion Discussions / General » Can someone please share a formula page?

THANKS!

by anon (guest), 03 Jul 2018 06:09
rafi levy (guest) 03 Jul 2018 05:56
in discussion Discussions / General » Can someone please share a formula page?

פורסם בקבוצת הווטצאפ

by rafi levy (guest), 03 Jul 2018 05:56
rafi levy (guest) 03 Jul 2018 05:40
in discussion Discussions / General » td lambda backward in ex. 7

yes, if you can explain delta_v (Part 2: solution 1) in terms of the definitions of Part1. Would it be correct to say that delta_v(s) = alpha * E_t_s * delta_t?

In addition, i think there is a missing gamma (as a multiplier) in the second expression in the bottom line in 1-3,

∆V (s1) = α ∗ (r1 + γ ∗ VT −1(s2) − VT −1(s1)) + α (r2 + γ ∗ VT −1(s3) − VT −1(s2)) [* gamma?]

otherwise v_t_1(s2) would not be cancelled

and another missing gamma in 1-4 in the last updates in delta_v(s2)

∆V (s2) = α ∗ (r2 + γ ∗ VT −1(s3) − VT −1(s2)) + α (r3 + γ ∗ VT −1(sF ) − VT −1(s3)) * [* gamma?]

otherwise v_t_1(s3) would not be cancelled

thanks
Rafi

by rafi levy (guest), 03 Jul 2018 05:40
Anon (guest) 03 Jul 2018 05:17
in discussion Discussions / General » Can someone please share a formula page?

Thanks!

Can someone please share a formula page? by Anon (guest), 03 Jul 2018 05:17
page 1123...next »