next up previous
Next: ALGORITHMS Up: PLANNING SIMPLE TRAJECTORIES USING Previous: ARCHITECTURE 2

OBJECTIVE FUNCTION

With both architectures we want to minimize
\begin{displaymath}
E^p = \sum_p \sum_{k=1}^{n+1} \frac{1}{2} (eval(s^p(k-1),s^p(k)))^2.
\end{displaymath} (3)

In words, we wish to find a sequence of subgoals such that the sum of the costs of all involved subprograms is minimized. This will be done by using gradient descent techniques to be described in the next section.



Juergen Schmidhuber 2003-03-14

Back to Subgoal learning - Hierarchical Learning
Pages with Subgoal learning pictures