CHARDA: Causal Hybrid Automata Recovery via Dynamic Analysis

TL;DR

CHARDA is a novel method that automatically learns hybrid automata by analyzing runtime data, identifying modes, and inferring causal transition conditions using information-theoretic measures.

Contribution

It introduces the use of information-theoretic measures for data segmentation, model selection, and causal inference in hybrid automata learning, with flexible extensions.

Findings

Successfully models complex character behavior in a videogame

Accurately learns modes of probabilistic timed automata in aircraft domain

Outperforms recent methods in automata learning

Abstract

We propose and evaluate a new technique for learning hybrid automata automatically by observing the runtime behavior of a dynamical system. Working from a sequence of continuous state values and predicates about the environment, CHARDA recovers the distinct dynamic modes, learns a model for each mode from a given set of templates, and postulates causal guard conditions which trigger transitions between modes. Our main contribution is the use of information-theoretic measures (1)~as a cost function for data segmentation and model selection to penalize over-fitting and (2)~to determine the likely causes of each transition. CHARDA is easily extended with different classes of model templates, fitting methods, or predicates. In our experiments on a complex videogame character, CHARDA successfully discovers a reasonable over-approximation of the character's true behaviors. Our results also compare favorably against recent work in automatically learning probabilistic timed automata in an aircraft domain: CHARDA exactly learns the modes of these simpler automata.