Next: Brief Introduction to Optimal
Bias-Optimal Incremental Problem Solving
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.
Given is a problem sequence and a probability distribution
) 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
a universal solver for arbitrary
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.
Back to OOPS home page