Verification of Safety in Artificial Intelligence and Reinforcement Learning Systems
Y. Kouskoulas, D. Genin, A. Schmidt, I. Papusha, R. Wu, G. Mullins, T. Young, and J. Brulé
Abstract
For complex artificially intelligent systems to be incorporated into applications where safety is critical, the systems must be safe and reliable. This article describes work a Johns Hopkins University Applied Physics Laboratory (APL) team is doing toward verifying safety in artificial intelligence and reinforcement learning systems.
Citation
Y. Kouskoulas, D. Genin, A. Schmidt, I. Papusha, R. Wu, G. Mullins, T. Young, and J. Brulé. “Verification of Safety in Artificial Intelligence and Reinforcement Learning Systems,” Johns Hopkins APL Technical Digest, Volume 35, Number 4, 2021.