Tree-Based Adaptive Model Learning

TL;DR

This paper introduces an enhanced learning algorithm that adapts to changing systems by reusing and updating learned models, demonstrating superior performance over existing methods in large, dynamic environments.

Contribution

The paper extends the Kearns-Vazirani algorithm to handle evolving systems and implements it in LearnLib, showcasing improved efficiency in adaptive learning scenarios.

Findings

Significant performance improvements over classic algorithms

Effective reuse and update of learned models

Successful application to large, dynamic examples

Abstract

We extend the Kearns-Vazirani learning algorithm to be able to handle systems that change over time. We present a new learning algorithm that can reuse and update previously learned behavior, implement it in the LearnLib library, and evaluate it on large examples, to which we make small adjustments between two runs of the algorithm. In these experiments our algorithm significantly outperforms both the classic Kearns-Vazirani learning algorithm and the current state-of-the-art adaptive algorithm.