 |
|
In 1987
Schmidhuber
published his first paper
on "Genetic Programming". His diploma thesis came out
in the same year and was more ambitious,
describing first general purpose learning algorithms:
Evolutionary principles in self-referential learning.
(On learning how to learn: The meta-meta-... hook.)
Diploma thesis, Institut f. Informatik, Tech. Univ. Munich, 1987.
Searchable PDF scan created by OCRmypdf which uses
LSTM.
(Or see jpeg scan below.)
Pages 7-13 are devoted to
the first self-improving, metalearning GP
approach that recursively applies metalevel GP
to the task of finding better program-modifying programs on lower levels.
The goal was "learning to learn" by using GP for improving GP.
|
|
|
Pages 23-51 are devoted to an alternative metalearning
approach called "prototypical self-referential learning mechanisms"
(PSALM 1 - PSALM 3). PSALMs use competing metalearning agents with
actions for generating and connecting agents and for assigning credit
to agents, subject to the constraint that total credit is conserved
(except for external reward and consumption). This was
the first credit-conserving
reinforcement learning economy.
|
|
|
