Algebraically Explainable Controllers: Decision Trees and Support Vector Machines Join Forces
This work addresses the problem of explainable AI in control systems for domains like robotics or automation, though it appears incremental as it builds on existing frameworks.
The paper tackles the challenge of creating explainable controllers for systems with complex continuous dynamics by combining decision trees and support vector machines, resulting in a method that produces understandable representations using algebraic predicates and is evaluated on established benchmarks.
Recently, decision trees (DT) have been used as an explainable representation of controllers (a.k.a. strategies, policies, schedulers). Although they are often very efficient and produce small and understandable controllers for discrete systems, complex continuous dynamics still pose a challenge. In particular, when the relationships between variables take more complex forms, such as polynomials, they cannot be obtained using the available DT learning procedures. In contrast, support vector machines provide a more powerful representation, capable of discovering many such relationships, but not in an explainable form. Therefore, we suggest to combine the two frameworks in order to obtain an understandable representation over richer, domain-relevant algebraic predicates. We demonstrate and evaluate the proposed method experimentally on established benchmarks.