Demo: dtControl: Decision tree learning algorithms for controller representation

Pranav Ashok; Mathias Jackermeier; Pushpak Jagtap; Jan KÅetínský; Maximilian Weininger; Majid Zamani

doi:10.1145/3365365.3383468

Demo: dtControl: Decision tree learning algorithms for controller representation

Pranav Ashok, Mathias Jackermeier, Pushpak Jagtap, Jan KÅetínský, Maximilian Weininger, Majid Zamani

Informatics 7 - Associate Professorship of Formal Methods for Software Reliability

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Decision tree learning is a popular classification technique most commonly used in machine learning applications. Recent work has shown that decision trees can be used to represent provably-correct controllers concisely. Compared to representations using lookup tables or binary decision diagrams, decision tree representations are smaller and more explainable. We present dtControl, an easily extensible tool offering a wide variety of algorithms for representing memoryless controllers as decision trees. We highlight that the trees produced by dtControl are often very concise with a single-digit number of decision nodes. This demo is based on our tool paper [1].

Original language	English
Title of host publication	HSCC 2020 - Proceedings of the 23rd International Conference on Hybrid Systems
Subtitle of host publication	Computation and Control ,part of CPS-IoT Week
Publisher	Association for Computing Machinery, Inc
ISBN (Electronic)	9781450370189
DOIs	https://doi.org/10.1145/3365365.3383468
State	Published - 22 Apr 2020
Event	23rd ACM International Conference on Hybrid Systems: Computation and Control, HSCC 2020, held as part of the 13th Cyber Physical Systems and Internet-of-Things Week, CPS-IoT Week 2020 - Sydney, Australia Duration: 21 Apr 2020 → 24 Apr 2020

Publication series

Name	HSCC 2020 - Proceedings of the 23rd International Conference on Hybrid Systems: Computation and Control ,part of CPS-IoT Week

Conference

Conference	23rd ACM International Conference on Hybrid Systems: Computation and Control, HSCC 2020, held as part of the 13th Cyber Physical Systems and Internet-of-Things Week, CPS-IoT Week 2020
Country/Territory	Australia
City	Sydney
Period	21/04/20 → 24/04/20

Keywords

controller representation
decision tree
explainability
machine learning
non-uniform quantizer
symbolic control

Access to Document

10.1145/3365365.3383468

Cite this

Ashok, P., Jackermeier, M., Jagtap, P., KÅetínský, J., Weininger, M., & Zamani, M. (2020). Demo: dtControl: Decision tree learning algorithms for controller representation. In HSCC 2020 - Proceedings of the 23rd International Conference on Hybrid Systems: Computation and Control ,part of CPS-IoT Week (HSCC 2020 - Proceedings of the 23rd International Conference on Hybrid Systems: Computation and Control ,part of CPS-IoT Week). Association for Computing Machinery, Inc. https://doi.org/10.1145/3365365.3383468

Ashok, Pranav ; Jackermeier, Mathias ; Jagtap, Pushpak et al. / Demo : dtControl: Decision tree learning algorithms for controller representation. HSCC 2020 - Proceedings of the 23rd International Conference on Hybrid Systems: Computation and Control ,part of CPS-IoT Week. Association for Computing Machinery, Inc, 2020. (HSCC 2020 - Proceedings of the 23rd International Conference on Hybrid Systems: Computation and Control ,part of CPS-IoT Week).

@inproceedings{97b8cb5e0a73416cbdfba93d11cb4d20,

title = "Demo: dtControl: Decision tree learning algorithms for controller representation",

abstract = "Decision tree learning is a popular classification technique most commonly used in machine learning applications. Recent work has shown that decision trees can be used to represent provably-correct controllers concisely. Compared to representations using lookup tables or binary decision diagrams, decision tree representations are smaller and more explainable. We present dtControl, an easily extensible tool offering a wide variety of algorithms for representing memoryless controllers as decision trees. We highlight that the trees produced by dtControl are often very concise with a single-digit number of decision nodes. This demo is based on our tool paper [1].",

keywords = "controller representation, decision tree, explainability, machine learning, non-uniform quantizer, symbolic control",

author = "Pranav Ashok and Mathias Jackermeier and Pushpak Jagtap and Jan K{\AA}et{\'i}nsk{\'y} and Maximilian Weininger and Majid Zamani",

note = "Publisher Copyright: {\textcopyright} 2020 Owner/Author.; 23rd ACM International Conference on Hybrid Systems: Computation and Control, HSCC 2020, held as part of the 13th Cyber Physical Systems and Internet-of-Things Week, CPS-IoT Week 2020 ; Conference date: 21-04-2020 Through 24-04-2020",

year = "2020",

month = apr,

day = "22",

doi = "10.1145/3365365.3383468",

language = "English",

series = "HSCC 2020 - Proceedings of the 23rd International Conference on Hybrid Systems: Computation and Control ,part of CPS-IoT Week",

publisher = "Association for Computing Machinery, Inc",

booktitle = "HSCC 2020 - Proceedings of the 23rd International Conference on Hybrid Systems",

}

Ashok, P, Jackermeier, M, Jagtap, P, KÅetínský, J, Weininger, M & Zamani, M 2020, Demo: dtControl: Decision tree learning algorithms for controller representation. in HSCC 2020 - Proceedings of the 23rd International Conference on Hybrid Systems: Computation and Control ,part of CPS-IoT Week. HSCC 2020 - Proceedings of the 23rd International Conference on Hybrid Systems: Computation and Control ,part of CPS-IoT Week, Association for Computing Machinery, Inc, 23rd ACM International Conference on Hybrid Systems: Computation and Control, HSCC 2020, held as part of the 13th Cyber Physical Systems and Internet-of-Things Week, CPS-IoT Week 2020, Sydney, Australia, 21/04/20. https://doi.org/10.1145/3365365.3383468

Demo: dtControl: Decision tree learning algorithms for controller representation. / Ashok, Pranav; Jackermeier, Mathias; Jagtap, Pushpak et al.
HSCC 2020 - Proceedings of the 23rd International Conference on Hybrid Systems: Computation and Control ,part of CPS-IoT Week. Association for Computing Machinery, Inc, 2020. (HSCC 2020 - Proceedings of the 23rd International Conference on Hybrid Systems: Computation and Control ,part of CPS-IoT Week).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Demo

T2 - 23rd ACM International Conference on Hybrid Systems: Computation and Control, HSCC 2020, held as part of the 13th Cyber Physical Systems and Internet-of-Things Week, CPS-IoT Week 2020

AU - Ashok, Pranav

AU - Jackermeier, Mathias

AU - Jagtap, Pushpak

AU - KÅetínský, Jan

AU - Weininger, Maximilian

AU - Zamani, Majid

PY - 2020/4/22

Y1 - 2020/4/22

N2 - Decision tree learning is a popular classification technique most commonly used in machine learning applications. Recent work has shown that decision trees can be used to represent provably-correct controllers concisely. Compared to representations using lookup tables or binary decision diagrams, decision tree representations are smaller and more explainable. We present dtControl, an easily extensible tool offering a wide variety of algorithms for representing memoryless controllers as decision trees. We highlight that the trees produced by dtControl are often very concise with a single-digit number of decision nodes. This demo is based on our tool paper [1].

AB - Decision tree learning is a popular classification technique most commonly used in machine learning applications. Recent work has shown that decision trees can be used to represent provably-correct controllers concisely. Compared to representations using lookup tables or binary decision diagrams, decision tree representations are smaller and more explainable. We present dtControl, an easily extensible tool offering a wide variety of algorithms for representing memoryless controllers as decision trees. We highlight that the trees produced by dtControl are often very concise with a single-digit number of decision nodes. This demo is based on our tool paper [1].

KW - controller representation

KW - decision tree

KW - explainability

KW - machine learning

KW - non-uniform quantizer

KW - symbolic control

UR - http://www.scopus.com/inward/record.url?scp=85086528231&partnerID=8YFLogxK

U2 - 10.1145/3365365.3383468

DO - 10.1145/3365365.3383468

M3 - Conference contribution

AN - SCOPUS:85086528231

T3 - HSCC 2020 - Proceedings of the 23rd International Conference on Hybrid Systems: Computation and Control ,part of CPS-IoT Week

BT - HSCC 2020 - Proceedings of the 23rd International Conference on Hybrid Systems

PB - Association for Computing Machinery, Inc

Y2 - 21 April 2020 through 24 April 2020

ER -

Ashok P, Jackermeier M, Jagtap P, KÅetínský J, Weininger M, Zamani M. Demo: dtControl: Decision tree learning algorithms for controller representation. In HSCC 2020 - Proceedings of the 23rd International Conference on Hybrid Systems: Computation and Control ,part of CPS-IoT Week. Association for Computing Machinery, Inc. 2020. (HSCC 2020 - Proceedings of the 23rd International Conference on Hybrid Systems: Computation and Control ,part of CPS-IoT Week). doi: 10.1145/3365365.3383468

Demo: dtControl: Decision tree learning algorithms for controller representation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this