Anja comments on A utility-maximizing varient of AIXI

Anja 20 Dec 2012 18:29 UTC
2 points

you forgot to multiply by 2^-l(q)

I think then you would count that twice, wouldn’t you? Because my original formula already contains the Solomonoff probability...
- AlexMennen 20 Dec 2012 21:18 UTC
  1 point
  Parent
  Oh right. But you still want the probability weighting to be inside the sum, so you would actually need
  $U\(\\\.\{y\}\\\.\{x\}\_\{<k\}y\\underline\{x\}\_\{k:m\_k\}\$
  =\frac{1}{\xi\left(\dot{y}\dot{x}_{%3Ck}y\underline{x}_{k:m_{k}}\right)}\sum_{q:q(y_{1:m_k})=x_{1:m_k}}%20U(q,y_{1:m_k})2%5E{-\ell\left(q\right)}%0A)
  - Anja 20 Dec 2012 21:36 UTC
    2 points
    Parent
    True. :)