short-paper

Open access

dtControl: decision tree learning algorithms for controller representation

Authors:

Mathias Jackermeier,

Pushpak Jagtap,

Jan Křetínský,

Maximilian Weininger,

Majid ZamaniAuthors Info & Claims

HSCC '20: Proceedings of the 23rd International Conference on Hybrid Systems: Computation and Control

Article No.: 17, Pages 1 - 7

https://doi.org/10.1145/3365365.3382220

Published: 22 April 2020 Publication History

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 trees are smaller and more explainable. We present dtControl, an easily extensible tool for representing memoryless controllers as decision trees. We give a comprehensive evaluation of various decision tree learning algorithms applied to 10 case studies arising out of correct-by-construction controller synthesis. These algorithms include two new techniques, one for using arbitrary linear binary classifiers in the decision tree learning, and one novel approach for determinizing controllers during the decision tree construction. In particular the latter turns out to be extremely efficient, yielding decision trees with a single-digit number of decision nodes on 5 of the case studies.

References

[1]

P. Ashok, T. Brázdil, K. Chatterjee, J. Křetínský, C. H. Lampert, and V. Toman. 2019. Strategy Representation by Decision Trees with Linear Classifiers. In QEST (1). Springer, 109--128.

[2]

Pranav Ashok, Mathias Jackermeier, Pushpak Jagtap, Jan Křetínský, Maximilian Weininger, and Majid Zamani. 2020. dtControl: Decision Tree Learning Algorithms for Controller Representation. arXiv:cs.LG/2002.04991

[3]

P. Ashok, J. Křetínský, K. G. Larsen, A. Le Coënt, J. H. Taankvist, and M. Weininger. 2019. SOS: Safe, Optimal and Small Strategies for Hybrid Markov Decision Processes. In QEST (1), D. Parker and V. Wolf (Eds.). Springer, 147--164.

[4]

R. Iris Bahar, Erica A. Frohm, Charles M. Gaona, Gary D. Hachtel, Enrico Macii, Abelardo Pardo, and Fabio Somenzi. 1997. Algebraic Decision Diagrams and Their Applications. Formal Methods in System Design 10, 2/3 (1997), 171--206.

Digital Library

[5]

C. Belta, B. Yordanov, and E. A. Gol. 2017. Formal methods for discrete-time dynamical systems. Vol. 89. Springer.

[6]

C. M. Bishop. 2007. Pattern recognition and machine learning, 5th Edition. Springer.

[7]

T. Brázdil, K. Chatterjee, M. Chmelik, A. Fellner, and J. Kretínský. 2015. Counterexample Explanation by Learning Small Strategies in Markov Decision Processes. In CAV (1) (Lecture Notes in Computer Science), Vol. 9206. Springer, 158--177.

[8]

T. Brázdil, K. Chatterjee, J. Kretínský, and V. Toman. 2018. Strategy Representation by Decision Trees in Reactive Synthesis. In TACAS (1) (Lecture Notes in Computer Science), Vol. 10805. Springer, 385--407.

[9]

L. Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone. 1984. Classification and Regression Trees. Wadsworth.

[10]

R. E. Bryant. 1986. Graph-based algorithms for boolean function manipulation. IEEE Trans. Comput. 100, 8 (1986), 677--691.

Digital Library

[11]

Ioannis T. Christou and Sofoklis Efremidis. 2007. An Evolving Oblique Decision Tree Ensemble Architecture for Continuous Learning Applications. In AIAI (IFIP), Vol. 247. Springer, 3--11.

[12]

A. David, P Gjøl Jensen, K. Guldstrand Larsen, M. Mikucionis, and J. H. Taankvist. 2015. Uppaal Stratego. In TACAS (Lecture Notes in Computer Science), Vol. 9035. Springer, 206--211.

[13]

Antoine Girard. 2013. Low-complexity quantized switching controllers using approximate bisimulation. Nonlinear Analysis: Hybrid Systems 10 (2013), 34--44.

[14]

Pushpak Jagtap, Fardin Abdi, Matthias Rungger, Majid Zamani, and Marco Caccamo. 2018. Software Fault Tolerance for Cyber-Physical Systems via Full System Restart. CoRR abs/1812.03546 (2018).

[15]

Pushpak Jagtap and Majid Zamani. 2017. QUEST: A Tool for State-Space Quantization-Free Synthesis of Symbolic Controllers. In QEST (Lecture Notes in Computer Science), Vol. 10503. Springer, 309--313.

[16]

Manuel Mazo Jr., Anna Davitian, and Paulo Tabuada. 2010. PESSOA: A Tool for Embedded Controller Synthesis. In CAV (Lecture Notes in Computer Science), Vol. 6174. Springer, 566--569.

[17]

Kyle D. Julian, Mykel J. Kochenderfer, and Michael P. Owen. 2018. Deep Neural Network Compression for Aircraft Collision Avoidance Systems. CoRR abs/1810.04240 (2018).

[18]

Mahmoud Khaled and Majid Zamani. 2019. pFaces: an acceleration ecosystem for symbolic control. In HSCC. ACM, 252--257.

[19]

Niels Landwehr, Mark A. Hall, and Eibe Frank. 2003. Logistic Model Trees. In ECML (Lecture Notes in Computer Science), Vol. 2837. Springer, 241--252.

[20]

Kim Guldstrand Larsen, Adrien Le Coënt, Marius Mikucionis, and Jakob Haahr Taankvist. 2018. Guaranteed Control Synthesis for Continuous Systems in Uppaal Tiga. In CyPhy/WESE (Lecture Notes in Computer Science), Vol. 11615. Springer, 113--133.

[21]

Kim Guldstrand Larsen, Marius Mikucionis, and Jakob Haahr Taankvist. 2015. Safe and Optimal Adaptive Cruise Control. In Correct System Design (Lecture Notes in Computer Science), Vol. 9360. Springer, 260--277.

[22]

Philipp J. Meyer, Matthias Rungger, Michael Luttenberger, Javier Esparza, and Majid Zamani. 2017. Quantitative Implementation Strategies for Safety Controllers. CoRR abs/1712.05278 (2017).

[23]

T. M. Mitchell. 1997. Machine learning. McGraw-Hill.

Digital Library

[24]

Sebti Mouelhi, Antoine Girard, and Gregor Gößler. 2013. CoSyMA: a tool for controller synthesis using multi-scale abstractions. In HSCC. ACM, 83--88.

[25]

S. K. Murthy, S. Kasif, S. Salzberg, and R. Beigel. 1993. OC1: A Randomized Induction of Oblique Decision Trees. In AAAI. AAAI Press / The MIT Press, 322--327.

[26]

G. N. Nair, F. Fagnani, S. Zampieri, and R. J. Evans. 2007. Feedback control under data rate constraints: An overview. Proc. of the IEEE 95, 1 (2007), 108--137.

[27]

Daniel Neider, Shambwaditya Saha, and P. Madhusudan. 2016. Synthesizing PieceWise Functions by Learning Classifiers. In TACAS (Lecture Notes in Computer Science), Vol. 9636. Springer, 186--203.

[28]

F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. 2011. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research 12 (2011), 2825--2830.

Digital Library

[29]

Larry D. Pyeatt and Adele E. Howe. 1998. Decision Tree Function Approximation in Reinforcement Learning. Technical Report. Computer Science Department, Colorado State University.

Digital Library

[30]

J. R. Quinlan. 1993. C4.5: Programs for Machine Learning. Morgan Kaufmann.

[31]

G. Reissig, A. Weber, and M. Rungger. 2016. Feedback refinement relations for the synthesis of symbolic controllers. IEEE Trans. Automat. Control 62, 4 (2016), 1781--1796.

[32]

M. Rungger and Zamani M. 2016. SCOTS: A Tool for the Synthesis of Symbolic Controllers. In HSCC. ACM, 99--104.

Digital Library

[33]

Matthias Rungger, Alexander Weber, and Gunther Reissig. 2015. State space grids for low complexity abstractions. In CDC. IEEE, 6139--6146.

[34]

Matthias Rungger and Majid Zamani. 2017. Invariance Feedback Entropy of Uncertain Control Systems. CoRR abs/1706.05242 (2017).

[35]

A. Swikir and M. Zamani. 2019. Compositional synthesis of symbolic models for networks of switched systems. IEEE Control Systems Letters 3, 4 (2019), 1056--1061.

[36]

P. Tabuada. 2009. Verification and control of hybrid systems: a symbolic approach. Springer Science & Business Media.

Digital Library

[37]

Paul E. Utgoff. 1988. Perceptron Trees: A Case Study In Hybrid Concept Representations. In AAAI. AAAI Press / The MIT Press, 601--606.

Digital Library

[38]

Ivan S. Zapreev, Cees Verdier, and Manuel Mazo Jr. 2018. Optimal Symbolic Controllers Determinization for BDD storage. In ADHS (IFAC-PapersOnLine), Vol. 51. Elsevier, 1--6.

[39]

Harry Zhang. 2004. The Optimality of Naive Bayes. In FLAIRS Conference. AAAI Press, 562--567.

Cited By

Abate AGiacobbe MSchnitzer Y(2024)Bisimulation LearningComputer Aided Verification10.1007/978-3-031-65633-0_8(161-183)Online publication date: 26-Jul-2024
https://doi.org/10.1007/978-3-031-65633-0_8
Bork AChakraborty DGrover KKřetínský JMohr S(2024)Learning Explainable and Better Performing Representations of POMDP StrategiesTools and Algorithms for the Construction and Analysis of Systems10.1007/978-3-031-57249-4_15(299-319)Online publication date: 5-Apr-2024
https://doi.org/10.1007/978-3-031-57249-4_15
Said AGöker H(2023)Spectral analysis and Bi-LSTM deep network-based approach in detection of mild cognitive impairment from electroencephalography signalsCognitive Neurodynamics10.1007/s11571-023-10010-y18:2(597-614)Online publication date: 3-Oct-2023
https://doi.org/10.1007/s11571-023-10010-y
Show More Cited By

Index Terms

dtControl: decision tree learning algorithms for controller representation
1. Computer systems organization
  1. Embedded and cyber-physical systems
2. Computing methodologies
  1. Artificial intelligence
    1. Control methods
  2. Machine learning
    1. Machine learning approaches
      1. Classification and regression trees

Recommendations

dtControl: decision tree learning algorithms for controller representation
HSCC '20: Proceedings of the 23rd International Conference on Hybrid Systems: Computation and Control

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 ...
An Efficient Algorithm for Generating Generalized Decision Forests

A shortcoming of univariate decision tree learners is that they do not learn intermediate concepts and select only one of the input features in the branching decision at each intermediate tree node. It has been empirically demonstrated that cascading ...
dtControl 2.0: Explainable Strategy Representation via Decision Tree Learning Steered by Experts
Tools and Algorithms for the Construction and Analysis of Systems
Abstract
Recent advances have shown how decision trees are apt data structures for concisely representing strategies (or controllers) satisfying various objectives. Moreover, they also make the strategy more explainable. The recent tool dtControl had ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

HSCC '20: Proceedings of the 23rd International Conference on Hybrid Systems: Computation and Control

April 2020

324 pages

ISBN:9781450370189

DOI:10.1145/3365365

Program Chairs:
Aaron Ames
California Institute of Technology
,
Sanjit A. Seshia
University of California, Berkeley
,
Publications Chair:
Jyotirmoy Deshmukh
University of Southern California

Copyright © 2020 Owner/Author.

This work is licensed under a Creative Commons Attribution International 4.0 License.

Sponsors

SIGBED: ACM Special Interest Group on Embedded Systems

Publisher

Association for Computing Machinery

New York, NY, United States

Publication Notes

Badge change: Article originally badged under Version 1.0 guidelines https://www.acm.org/publications/policies/artifact-review-badging

Publication History

Published: 22 April 2020

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Badges

Results Reproduced / v1.1

Author Tags

Qualifiers

Short-paper

Funding Sources

Conference

HSCC '20

Sponsor:

SIGBED

HSCC '20: 23rd ACM International Conference on Hybrid Systems: Computation and Control

April 22 - 24, 2020

New South Wales, Sydney, Australia

Acceptance Rates

Overall Acceptance Rate 153 of 373 submissions, 41%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

9
Total Citations
View Citations
800
Total Downloads

Downloads (Last 12 months)135
Downloads (Last 6 weeks)25

Reflects downloads up to 16 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

Abate AGiacobbe MSchnitzer Y(2024)Bisimulation LearningComputer Aided Verification10.1007/978-3-031-65633-0_8(161-183)Online publication date: 26-Jul-2024
https://doi.org/10.1007/978-3-031-65633-0_8
Bork AChakraborty DGrover KKřetínský JMohr S(2024)Learning Explainable and Better Performing Representations of POMDP StrategiesTools and Algorithms for the Construction and Analysis of Systems10.1007/978-3-031-57249-4_15(299-319)Online publication date: 5-Apr-2024
https://doi.org/10.1007/978-3-031-57249-4_15
Said AGöker H(2023)Spectral analysis and Bi-LSTM deep network-based approach in detection of mild cognitive impairment from electroencephalography signalsCognitive Neurodynamics10.1007/s11571-023-10010-y18:2(597-614)Online publication date: 3-Oct-2023
https://doi.org/10.1007/s11571-023-10010-y
Kiesbye JGrover KAshok PKretinsky J(2022)Planning via model checking with decision-tree controllers2022 International Conference on Robotics and Automation (ICRA)10.1109/ICRA46639.2022.9811980(4347-4354)Online publication date: 23-May-2022
https://doi.org/10.1109/ICRA46639.2022.9811980
Tomar MKawan CZamani M(2022)Numerical over-approximation of invariance entropy via finite abstractionsSystems & Control Letters10.1016/j.sysconle.2022.105395170(105395)Online publication date: Dec-2022
https://doi.org/10.1016/j.sysconle.2022.105395
Gu RJensen PSeceleanu CEnoiu ELundqvist K(2022)Correctness-Guaranteed Strategy Synthesis and Compression for Multi-Agent Autonomous SystemsScience of Computer Programming10.1016/j.scico.2022.102894(102894)Online publication date: Oct-2022
https://doi.org/10.1016/j.scico.2022.102894
Ivanova ESaoud AGirard A(2022)Lazy controller synthesis for monotone transition systems and directed safety specificationsAutomatica10.1016/j.automatica.2021.109993135(109993)Online publication date: Jan-2022
https://doi.org/10.1016/j.automatica.2021.109993
Müezzinoğlu TKaraköse M(2021)An Intelligent Human–Unmanned Aerial Vehicle Interaction Approach in Real Time Based on Machine Learning Using Wearable GlovesSensors10.3390/s2105176621:5(1766)Online publication date: 4-Mar-2021
https://doi.org/10.3390/s21051766
Ashok PJackermeier MKřetínský JWeinhuber CWeininger MYadav M(2021)dtControl 2.0: Explainable Strategy Representation via Decision Tree Learning Steered by ExpertsTools and Algorithms for the Construction and Analysis of Systems10.1007/978-3-030-72013-1_17(326-345)Online publication date: 23-Mar-2021
https://doi.org/10.1007/978-3-030-72013-1_17

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents