English

Revisiting Robustness in Priced Timed Games

Logic in Computer Science 2015-07-22 v1 Formal Languages and Automata Theory

Abstract

Priced timed games are optimal-cost reachability games played between two players---the controller and the environment---by moving a token along the edges of infinite graphs of configurations of priced timed automata. The goal of the controller is to reach a given set of target locations as cheaply as possible, while the goal of the environment is the opposite. Priced timed games are known to be undecidable for timed automata with 33 or more clocks, while they are known to be decidable for automata with 11 clock. In an attempt to recover decidability for priced timed games Bouyer, Markey, and Sankur studied robust priced timed games where the environment has the power to slightly perturb delays proposed by the controller. Unfortunately, however, they showed that the natural problem of deciding the existence of optimal limit-strategy---optimal strategy of the controller where the perturbations tend to vanish in the limit---is undecidable with 1010 or more clocks. In this paper we revisit this problem and improve our understanding of the decidability of these games. We show that the limit-strategy problem is already undecidable for a subclass of robust priced timed games with 55 or more clocks. On a positive side, we show the decidability of the existence of almost optimal strategies for the same subclass of one-clock robust priced timed games by adapting a classical construction by Bouyer at al. for one-clock priced timed games.

Keywords

Cite

@article{arxiv.1507.05787,
  title  = {Revisiting Robustness in Priced Timed Games},
  author = {Shibashis Guha and Shankara Narayanan Krishna and Lakshmi Manasa and Ashutosh Trivedi},
  journal= {arXiv preprint arXiv:1507.05787},
  year   = {2015}
}
R2 v1 2026-06-22T10:15:35.367Z