|
|
|
Note here that the sequence
of actions precomputed by the agent.
|
|
Subsequent actions are
returned off of the queue, without recomputation.
|
|
Only when the queue of
actions is exhausted does the S-P-S-A compute new moves.
|
|
To think about: what does
this mean in terms of unexpected results of actions and noisy environments?
|
