0
$\begingroup$

enter image description here

I don't understand the last equality.

Here is my derivation $r(s,a,s')=\sum_{r\in R} r p(r|s,a,s')=\sum_{r\in R} r \frac{p(s,a,s'|r)p(r)}{p(s,a,s')}$

Could you give me the correct steps to derive them?

Thank you

Improve this question
$\endgroup$
2

1 Answer 1

Reset to default
0
$\begingroup$

I found out that

$\sum_{r\in R} r p(r|s,a,s') = \sum_{r\in R} r \frac{p(s,a,s',r)}{p(s,a,s')} = \sum_{r\in R} r \frac{p(s',r|s,a)}{p(s'|s,a)} $ by cancelling $p(s,a)$.

Improve this answer
$\endgroup$

Not the answer you're looking for? Browse other questions tagged .