Strategy representation by decision trees with linear classifiers

P. Ashok, T. Brázdil, K. Chatterjee, J. Křetínský, C. Lampert, V. Toman, in:, 16th International Conference on Quantitative Evaluation of Systems, Springer Nature, 2019, pp. 109–128.


Conference Paper | Published | English
Author
; ; ; ; ;
Series Title
LNCS
Abstract
Graph games and Markov decision processes (MDPs) are standard models in reactive synthesis and verification of probabilistic systems with nondeterminism. The class of 𝜔 -regular winning conditions; e.g., safety, reachability, liveness, parity conditions; provides a robust and expressive specification formalism for properties that arise in analysis of reactive systems. The resolutions of nondeterminism in games and MDPs are represented as strategies, and we consider succinct representation of such strategies. The decision-tree data structure from machine learning retains the flavor of decisions of strategies and allows entropy-based minimization to obtain succinct trees. However, in contrast to traditional machine-learning problems where small errors are allowed, for winning strategies in graph games and MDPs no error is allowed, and the decision tree must represent the entire strategy. In this work we propose decision trees with linear classifiers for representation of strategies in graph games and MDPs. We have implemented strategy representation using this data structure and we present experimental results for problems on graph games and MDPs, which show that this new data structure presents a much more efficient strategy representation as compared to standard decision trees.
Publishing Year
Date Published
2019-09-04
Proceedings Title
16th International Conference on Quantitative Evaluation of Systems
Volume
11785
Page
109-128
Conference
QEST: Quantitative Evaluation of Systems
Conference Location
Glasgow, United Kingdom
Conference Date
2019-09-10 – 2019-09-12
ISSN
IST-REx-ID

Cite this

Ashok P, Brázdil T, Chatterjee K, Křetínský J, Lampert C, Toman V. Strategy representation by decision trees with linear classifiers. In: 16th International Conference on Quantitative Evaluation of Systems. Vol 11785. Springer Nature; 2019:109-128. doi:10.1007/978-3-030-30281-8_7
Ashok, P., Brázdil, T., Chatterjee, K., Křetínský, J., Lampert, C., & Toman, V. (2019). Strategy representation by decision trees with linear classifiers. In 16th International Conference on Quantitative Evaluation of Systems (Vol. 11785, pp. 109–128). Glasgow, United Kingdom: Springer Nature. https://doi.org/10.1007/978-3-030-30281-8_7
Ashok, Pranav, Tomáš Brázdil, Krishnendu Chatterjee, Jan Křetínský, Christoph Lampert, and Viktor Toman. “Strategy Representation by Decision Trees with Linear Classifiers.” In 16th International Conference on Quantitative Evaluation of Systems, 11785:109–28. Springer Nature, 2019. https://doi.org/10.1007/978-3-030-30281-8_7.
P. Ashok, T. Brázdil, K. Chatterjee, J. Křetínský, C. Lampert, and V. Toman, “Strategy representation by decision trees with linear classifiers,” in 16th International Conference on Quantitative Evaluation of Systems, Glasgow, United Kingdom, 2019, vol. 11785, pp. 109–128.
Ashok P, Brázdil T, Chatterjee K, Křetínský J, Lampert C, Toman V. 2019. Strategy representation by decision trees with linear classifiers. 16th International Conference on Quantitative Evaluation of Systems. QEST: Quantitative Evaluation of Systems, LNCS, vol. 11785. 109–128.
Ashok, Pranav, et al. “Strategy Representation by Decision Trees with Linear Classifiers.” 16th International Conference on Quantitative Evaluation of Systems, vol. 11785, Springer Nature, 2019, pp. 109–28, doi:10.1007/978-3-030-30281-8_7.

Link(s) to Main File(s)
Access Level
OA Open Access

Export

Marked Publications

Open Data IST Research Explorer

Sources

arXiv 1906.08178

Search this title in

Google Scholar
ISBN Search