Shifting Inductive Bias with Success-Story Algorithm, Adaptive Levin Search, and Incremental Self-Improvement
Created by W.Langdon from
gp-bibliography.bib Revision:1.8081
- @Article{Schmidhuber:1997:ML,
-
author = "Juergen Schmidhuber and Jieyu Zhao and Marco Wiering",
-
title = "Shifting Inductive Bias with Success-Story Algorithm,
Adaptive {Levin} Search, and Incremental
Self-Improvement",
-
journal = "Machine Learning",
-
year = "1997",
-
volume = "28",
-
number = "1",
-
pages = "105--130",
-
month = jul,
-
keywords = "genetic algorithms, genetic programming, inductive
bias, reinforcement learning, reward acceleration,
Levin search, success-story algorithm, incremental
self-improvement",
-
ISSN = "0885-6125",
-
URL = "ftp://ftp.idsia.ch/pub/juergen/mljssalevin.pdf",
-
URL = "http://www.idsia.ch/~juergen/mljssalevin/",
-
URL = "https://rdcu.be/dVjRV",
-
DOI = "doi:10.1023/A:1007383707642",
-
size = "30 pages",
-
abstract = "We study task sequences that allow for speeding up the
learner's average reward intake through appropriate
shifts of inductive bias (changes of the learner's
policy). To evaluate long-term effects of bias shifts
setting the stage for later bias shifts we use the
success-story algorithm (SSA). SSA is occasionally
called at times that may depend on the policy itself.
It uses backtracking to undo those bias shifts that
have not been empirically observed to trigger long-term
reward accelerations (measured up until the current SSA
call). Bias shifts that survive SSA represent a
lifelong success history. Until the next SSA call, they
are considered useful and build the basis for
additional bias shifts. SSA allows for plugging in a
wide variety of learning algorithms. We plug in (1) a
novel, adaptive extension of Levin search and (2) a
method for embedding the learner's policy modification
strategy within the policy itself (incremental
self-improvement). Our inductive transfer case studies
involve complex, partially observable environments
where traditional reinforcement learning fails.",
-
notes = "IDSIA, Corso Elvezia 36, CH-6900-Lugano, Switzerland",
- }
Genetic Programming entries for
Jurgen Schmidhuber
Jieyu Zhao
Marco Wiering
Citations