**Jürgen
Schmidhuber
IDSIA, Galleria 2, 6928 Manno-Lugano, Switzerland
**

In S. Becker, S. Thrun, K. Obermayer, eds.,
*Advances in Neural Information Processing Systems 15, NIPS'15,*
MIT Press, Cambridge MA, p. 1571-1578, 2003.
PS.
PDF.

Given is a problem sequence and a probability distribution
(the *bias*) on programs computing solution candidates.
We present an optimally fast way of incrementally solving
each task in the sequence.
Bias shifts are computed by program prefixes that
modify the distribution on their suffixes by
reusing successful code for previous tasks
(stored in non-modifiable memory).
No tested program gets more
runtime than its probability times the total search time.
In illustrative experiments, ours becomes the first general system to
*learn* a universal solver for arbitrary disk
*Towers of Hanoi* tasks (minimal solution size ).
It demonstrates the advantages of incremental learning by
profiting from previously solved, simpler tasks involving
samples of a simple context free language.

- Brief Introduction to Optimal Universal Search
- Optimal Ordered Problem Solver (OOPS)
- OOPS Prerequisites: Multitasking & Prefix Tracking Through Method ``Try''
- OOPS For Finding Universal Solvers

- A Particular Initial Programming Language
- Experiments: Towers of Hanoi and Context-Free Symmetry
- Bibliography
- About this document ...

Juergen Schmidhuber 2003-02-25

Back to OOPS home page