@inproceedings{b3a6c399b0ee4e2e97b0b28f466e413d,
title = "Synthesis of Safe, Optimal and Compact Strategies for Stochastic Hybrid Games",
abstract = "UPPAAL-Stratego is a recent branch of the verification tool UPPAAL allowing for synthesis of safe and optimal strategies for stochastic timed (hybrid) games. We describe newly developed learning methods, allowing for synthesis of significantly better strategies and with much improved convergence behaviour. Also, we describe novel use of decision trees for learning orders-of-magnitude more compact strategy representation. In both cases, the seek for optimality does not compromise safety.",
keywords = "M-learning, Q-learning, Reinforcement learning, Stochastic hybrid grame, Symbolic synthesis, Timed automata",
author = "Larsen, {Kim Guldstrand}",
year = "2019",
doi = "10.4230/LIPIcs.CONCUR.2019.2",
language = "English",
isbn = "978-3-95977-121-4",
series = "Leibniz International Proceedings in Informatics",
publisher = "Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing",
editor = "Wan Fokkink and {van Glabbeek}, Rob",
booktitle = "Proceedings of 30th International Conference on Concurrency Theory, CONCUR 2019",
note = "30th International Conference on Concurrency Theory, CONCUR 2019 ; Conference date: 27-08-2019 Through 30-08-2019",
}