Next: OBJECTIVE FUNCTION
Up: TWO SUBGOAL CREATING ARCHITECTURES
Previous: ARCHITECTURE 1
Figure 3 shows a recurrent subgoal generator (a
back-prop net that feeds its output back to part of its input).
With problem ,
the input vector of at the first `time step' of the sequential
subgoal generation process is
. The output of is .
At time step
, the input of is
. Its output is
Again we use
A recurrent subgoal generator emitting an arbitrary number
of subgoals in response to a start/goal combination.
Each subgoal is fed back to the START-input of the
subgoal generator. The dashed line indicates that
the evaluator needs to see the GOAL at the last step
of the subgoal generation process. See text for details.
Check out Schmidhuber's Habilitation thesis for pictures.
Back to Subgoal learning - Hierarchical Learning
Pages with Subgoal learning pictures