dtControl 2.0: Explainable Strategy Representation via Decision
Tree Learning Steered by Experts

D 2021

dtControl 2.0: Explainable Strategy Representation via Decision Tree Learning Steered by Experts

ASHOK, Pranav; Mathias JACKERMEIER; Jan KŘETÍNSKÝ; Christoph WEINHUBER; Maximilian WEININGER et al.

Základní údaje

Originální název

dtControl 2.0: Explainable Strategy Representation via Decision Tree Learning Steered by Experts

Autoři

ASHOK, Pranav; Mathias JACKERMEIER; Jan KŘETÍNSKÝ; Christoph WEINHUBER; Maximilian WEININGER a Mayank YADAV

Vydání

Tools and Algorithms for the Construction and Analysis of Systems - 27th International Conference, TACAS 2021, Held as Part of the European Joint Conferences on Theory and Practice of Software, ETAPS 2021, Luxembourg City, Luxembourg, March 27 - April 1, 2021, Proceedings, Part II, od s. 326-345, 20 s. 2021

Nakladatel

Springer

Další údaje

Typ výsledku

Stať ve sborníku

Označené pro přenos do RIV

Organizační jednotka

Fakulta informatiky

ISBN

9783030720124

ISSN

DOI

https://doi.org/10.1007/978-3-030-72013-1_17

Změněno: 17. 3. 2025 14:43, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

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 provided pipelines with tools supporting strategy synthesis for hybrid systems, such as SCOTS and Uppaal Stratego. We present dtControl 2.0, a new version with several fundamentally novel features. Most importantly, the user can now provide domain knowledge to be exploited in the decision tree learning process and can also interactively steer the process based on the dynamically provided information. To this end, we also provide a graphical user interface. It allows for inspection and re-computation of parts of the result, suggesting as well as receiving advice on predicates, and visual simulation of the decision-making process. Besides, we interface model checkers of probabilistic systems, namely STORM and PRISM and provide dedicated support for categorical enumeration-type state variables. Consequently, the controllers are more explainable and smaller.

Citovat

ASHOK, Pranav; Mathias JACKERMEIER; Jan KŘETÍNSKÝ; Christoph WEINHUBER; Maximilian WEININGER a Mayank YADAV. dtControl 2.0: Explainable Strategy Representation via Decision Tree Learning Steered by Experts. In Tools and Algorithms for the Construction and Analysis of Systems - 27th International Conference, TACAS 2021, Held as Part of the European Joint Conferences on Theory and Practice of Software, ETAPS 2021, Luxembourg City, Luxembourg, March 27 - April 1, 2021, Proceedings, Part II. Springer, 2021, s. 326-345. ISBN 9783030720124. Dostupné z: https://doi.org/10.1007/978-3-030-72013-1_17.

@inproceedings{2484786,
   author = {Ashok, Pranav and Jackermeier, Mathias and Křetínský, Jan and Weinhuber, Christoph and Weininger, Maximilian and Yadav, Mayank},
   booktitle = {Tools and Algorithms for the Construction and Analysis of Systems - 27th International Conference, TACAS 2021, Held as Part of the European Joint Conferences on Theory and Practice of Software, ETAPS 2021, Luxembourg City, Luxembourg, March 27 - April 1, 2021, Proceedings, Part II},
   doi = {https://doi.org/10.1007/978-3-030-72013-1_17},
   isbn = {9783030720124},
   pages = {326-345},
   publisher = {Springer},
   title = {dtControl 2.0: Explainable Strategy Representation via Decision Tree Learning Steered by Experts},
   year = {2021}
}

TY  - CONF
ID  - 2484786
AU  - Ashok, Pranav - Jackermeier, Mathias - Křetínský, Jan - Weinhuber, Christoph - Weininger, Maximilian - Yadav, Mayank
PY  - 2021
TI  - dtControl 2.0: Explainable Strategy Representation via Decision Tree Learning Steered by Experts
PB  - Springer
SN  - 9783030720124
N2  - 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 provided pipelines with tools supporting strategy synthesis for hybrid systems, such as SCOTS and Uppaal Stratego. We present dtControl 2.0, a new version with several fundamentally novel features. Most importantly, the user can now provide domain knowledge to be exploited in the decision tree learning process and can also interactively steer the process based on the dynamically provided information. To this end, we also provide a graphical user interface. It allows for inspection and re-computation of parts of the result, suggesting as well as receiving advice on predicates, and visual simulation of the decision-making process. Besides, we interface model checkers of probabilistic systems, namely STORM and PRISM and provide dedicated support for categorical enumeration-type state variables. Consequently, the controllers are more explainable and smaller.
ER  -

ASHOK, Pranav; Mathias JACKERMEIER; Jan KŘETÍNSKÝ; Christoph WEINHUBER; Maximilian WEININGER a Mayank YADAV. dtControl 2.0: Explainable Strategy Representation via Decision Tree Learning Steered by Experts. In \textit{Tools and Algorithms for the Construction and Analysis of Systems - 27th International Conference, TACAS 2021, Held as Part of the European Joint Conferences on Theory and Practice of Software, ETAPS 2021, Luxembourg City, Luxembourg, March 27 - April 1, 2021, Proceedings, Part II}. Springer, 2021, s.~326-345. ISBN~9783030720124. Dostupné z: https://doi.org/10.1007/978-3-030-72013-1\_{}17.

Přehled o publikaci