Slides in PDF - of Marcus Hutter
Slides in PDF - of Marcus Hutter
Slides in PDF - of Marcus Hutter
You also want an ePaper? Increase the reach of your titles
YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.
<strong>Marcus</strong> <strong>Hutter</strong> - 71 - Universal Induction & Intelligence<br />
Optimal Policy and Value<br />
The σ-optimal policy p σ := arg max p V p σ<br />
maximizes V p σ ≤ V ∗ σ := V pσ<br />
σ .<br />
Explicit expressions for the action y k <strong>in</strong> cycle k <strong>of</strong> the σ-optimal policy<br />
p σ and their value Vσ<br />
∗ are<br />
∑ ∑ ∑<br />
y k = arg max max ... max (r k + ... +r m )·σ(x k:m |y 1:m x