On the Solvability of Inductive Problems: A Study in Epistemic Topology
Logic in Computer Science
2016-06-27 v1 Machine Learning
Abstract
We investigate the issues of inductive problem-solving and learning by doxastic agents. We provide topological characterizations of solvability and learnability, and we use them to prove that AGM-style belief revision is "universal", i.e., that every solvable problem is solvable by AGM conditioning.
Keywords
Cite
@article{arxiv.1606.07518,
title = {On the Solvability of Inductive Problems: A Study in Epistemic Topology},
author = {Alexandru Baltag and Nina Gierasimczuk and Sonja Smets},
journal= {arXiv preprint arXiv:1606.07518},
year = {2016}
}
Comments
In Proceedings TARK 2015, arXiv:1606.07295