Next: Semantics of Instruction Heads
Up: Appendix
Previous: Basic Cycle of Operations
At a given time LEFT's current stack will be either empty or
of the form ,
, where
(
) is of the form
Here denotes the -th checkpoint still in LEFT's
stack (compare section refis), denotes LEFT's
reward until time , (
) is the address of the -th LEFT-column modified in
between and the subsequent checkpoint, and
is the corresponding previous LEFT-column. The
pairs
were saved on the stack by the
first LI that changed the corresponding LEFT-columns after
.
The procedures SSALEFT() and SSARIGHT() below will be
invoked by module-modifying instructions to be discussed later.
SSALEFT():
- 1.
- If BlockSSALEFT TRUE then exit. Else:
- 2.
- Set BlockSSALEFT TRUE. Set variable equal to
current time ( is a new checkpoint). Use backtracking and the
information in Stack to undo as many of the most
recent -modifications as necessary to achieve SSC --
see inequality (1) in section 3. Pop off the corresponding
blocks in Stack. This procedure guarantees that SSC
will eventually be satisfied -- see, for example,
[35].
- 3.
- Push and onto Stack. They are the first
two elements of the next block to be pushed.
SSARIGHT() is analogous to SSALEFT().
Next: Semantics of Instruction Heads
Up: Appendix
Previous: Basic Cycle of Operations
Juergen Schmidhuber
2003-03-10
Back to Active Learning - Exploration - Curiosity page