On Learning How to Learn Learning Strategies Technical Report Fki-198-94 (revised)

  title={On Learning How to Learn Learning Strategies Technical Report Fki-198-94 (revised)},
  author={urgen Schmidhuber},
  • urgen Schmidhuber
  • Published 1995
This paper introduces the \incremental self-improvement paradigm". Unlike previous methods, incremental self-improvement encourages a reinforcement learning system to improve the way it learns, and to improve the way it improves the way it learns ..., without signiicant theoretical limitations | the system is able to \shift its inductive bias" in a universal way. Its major features are: (1) There is no explicit diierence between \learning", \meta-learning", and other kinds of information… CONTINUE READING
Highly Cited
This paper has 87 citations. REVIEW CITATIONS


Publications citing this paper.

87 Citations

Citations per Year
Semantic Scholar estimates that this publication has 87 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 30 references

Genetic evolution and co-evolution of computer programs

  • J. R. Koza
  • 1992
Highly Influential
4 Excerpts

A system for incremental learning based on algorithmic probability

  • R. Solomono
  • 1990
Highly Influential
4 Excerpts

Laws of information (nongrowth) and aspects of the foundation of probability

  • L. A. Levin
  • 1974
Highly Influential
4 Excerpts

Similar Papers

Loading similar papers…