Computer Science – Artificial Intelligence
Scientific paper
2002-07-31
Machine Learning, 54, 211-254, 2004.
Computer Science
Artificial Intelligence
43 pages, 2 figures, short version at NIPS 2002 (added 1 figure and references; streamlined presentation)
Scientific paper
We present a novel, general, optimally fast, incremental way of searching for a universal algorithm that solves each task in a sequence of tasks. The Optimal Ordered Problem Solver (OOPS) continually organizes and exploits previously found solutions to earlier tasks, efficiently searching not only the space of domain-specific algorithms, but also the space of search algorithms. Essentially we extend the principles of optimal nonincremental universal search to build an incremental universal learner that is able to improve itself through experience. In illustrative experiments, our self-improver becomes the first general system that learns to solve all n disk Towers of Hanoi tasks (solution size 2^n-1) for n up to 30, profiting from previously solved, simpler tasks involving samples of a simple context free language.
No associations
LandOfFree
Optimal Ordered Problem Solver does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Optimal Ordered Problem Solver, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Optimal Ordered Problem Solver will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-476613