Explaining Control Policies through Predicate Decision Diagrams

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F25%3A00143612" target="_blank" >RIV/00216224:14330/25:00143612 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1145/3716863.3718049" target="_blank" >http://dx.doi.org/10.1145/3716863.3718049</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3716863.3718049" target="_blank" >10.1145/3716863.3718049</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Explaining Control Policies through Predicate Decision Diagrams

Popis výsledku v původním jazyce

Safety-critical controllers of complex systems are hard to construct manually. Automated approaches such as controller synthesis or learning provide a tempting alternative but usually lack explainability. To this end, learning decision trees (DTs) has been prevalently used towards an interpretable model of the generated controllers. However, DTs do not exploit shared decision making, a key concept exploited in binary decision diagrams (BDDs) to reduce their size and thus improve explainability. In this work, we introduce predicate decision diagrams (PDDs) that extend BDDs with predicates and thus unite the advantages of DTs and BDDs for controller representation. We establish a synthesis pipeline for efficient construction of PDDs from DTs representing controllers, exploiting reduction techniques for BDDs also for PDDs.

Název v anglickém jazyce

Explaining Control Policies through Predicate Decision Diagrams

Popis výsledku anglicky

Safety-critical controllers of complex systems are hard to construct manually. Automated approaches such as controller synthesis or learning provide a tempting alternative but usually lack explainability. To this end, learning decision trees (DTs) has been prevalently used towards an interpretable model of the generated controllers. However, DTs do not exploit shared decision making, a key concept exploited in binary decision diagrams (BDDs) to reduce their size and thus improve explainability. In this work, we introduce predicate decision diagrams (PDDs) that extend BDDs with predicates and thus unite the advantages of DTs and BDDs for controller representation. We establish a synthesis pipeline for efficient construction of PDDs from DTs representing controllers, exploiting reduction techniques for BDDs also for PDDs.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

V - Vyzkumna aktivita podporovana z jinych verejnych zdroju

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

HSCC '25: Proceedings of the 28th ACM International Conference on Hybrid Systems: Computation and Control

ISBN

9798400715044

ISSN

—

e-ISSN

—

Počet stran výsledku

12

Strana od-do

1-12

Název nakladatele

Association for Computing Machinery

Místo vydání

Irvine, USA

Místo konání akce

Irvine, CA

Datum konání akce

1. 1. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001528165000004