no code implementations • 20 Mar 2024 • Luca Giamattei, Matteo Biagiola, Roberto Pietrantuono, Stefano Russo, Paolo Tonella
Our extension aims at eliminating some of the possible reasons for the poor performance of RL observed in our replication: (1) the presence of reward components providing contrasting or useless feedback to the RL agent; (2) the usage of an RL algorithm (Q-learning) which requires discretization of an intrinsically continuous state space.
no code implementations • 20 Jul 2023 • Matteo Biagiola, Paolo Tonella
State-of-the-art ADS testing approaches modify the controllable attributes of a simulated driving environment until the ADS misbehaves.
1 code implementation • 22 May 2023 • Matteo Biagiola, Paolo Tonella
The failure prediction acts as a fitness function, guiding the generation towards failure environment configurations, while saving computation time by deferring the execution of the DRL agent in the environment to those configurations that are more likely to expose failures.
1 code implementation • 14 May 2023 • Matteo Biagiola, Andrea Stocco, Vincenzo Riccio, Paolo Tonella
Our empirical evaluation shows that the ensemble failure predictor by the digital siblings is superior to each individual simulator at predicting the failures of the digital twin.