no code implementations • 27 Jul 2022 • Masaki Waga, Ezequiel Castellano, Sasinee Pruekprasert, Stefan Klikovits, Toru Takisaka, Ichiro Hasuo
The dynamic shielding technique constructs an approximate system model in parallel with RL using a variant of the RPNI algorithm and suppresses undesired explorations due to the shield constructed from the learned model.
no code implementations • 21 Jan 2022 • Sasinee Pruekprasert, Jérémy Dubut, Toru Takisaka, Clovis Eberhart, Ahmet Cetinkaya
We develop a method to approximate the moments of a discrete-time stochastic polynomial system.
no code implementations • 20 Dec 2021 • Sasinee Pruekprasert, Kai Cai
We propose sufficient conditions for verifying opacity of the global system model based only on the opacity of the local systems.
no code implementations • 30 Mar 2021 • Sasinee Pruekprasert, Clovis Eberhart, Jérémy Dubut
We extend previous work on symbolic self-triggered control for non-deterministic continuous-time nonlinear systems without stability assumptions to a larger class of specifications.