How to certify machine learning based safety-critical systems? A systematic literature review

F Tambon, G Laberge, L An, A Nikanjam… - Automated Software …, 2022 - Springer
Abstract Context Machine Learning (ML) has been at the heart of many innovations over the
past years. However, including it in so-called “safety-critical” systems such as automotive or …

Model-Free λ-Policy Iteration for Discrete-Time Linear Quadratic Regulation

Y Yang, B Kiumarsi, H Modares… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
This article presents a model-free-policy iteration (-PI) for the discrete-time linear quadratic
regulation (LQR) problem. To solve the algebraic Riccati equation arising from solving the …

Cooperative finitely excited learning for dynamical games

Y Yang, H Modares, KG Vamvoudakis… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
In this article, we propose a way to enhance the learning framework for zero-sum games
with dynamics evolving in continuous time. In contrast to the conventional centralized actor …

Robust actor–critic learning for continuous-time nonlinear systems with unmodeled dynamics

Y Yang, W Gao, H Modares… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
This article considers the robust optimal control problem for a class of nonlinear systems in
the presence of unmodeled dynamics. An adaptive optimal controller is designed using the …

Data-driven inverse reinforcement learning control for linear multiplayer games

B Lian, VS Donge, FL Lewis, T Chai… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
This article proposes a data-driven inverse reinforcement learning (RL) control algorithm for
nonzero-sum multiplayer games in linear continuous-time differential dynamical systems …

Adaptive fuzzy leader–follower synchronization of constrained heterogeneous multiagent systems

Y Yang, CZ Xu - IEEE Transactions on Fuzzy Systems, 2020 - ieeexplore.ieee.org
This article considers the distributed adaptive neuro-fuzzy output feedback control protocol
design to solve the output synchronization problem for heterogeneous multiagent systems …

Safety-aware pursuit-evasion games in unknown environments using gaussian processes and finite-time convergent reinforcement learning

NMT Kokolakis, KG Vamvoudakis - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
This article develops a safe pursuit-evasion game for enabling finite-time capture, optimal
performance as well as adaptation to an unknown cluttered environment. The pursuit …

Adaptive dynamic programming for optimal control of discrete‐time nonlinear system with state constraints based on control barrier function

J Xu, J Wang, J Rao, Y Zhong… - International Journal of …, 2022 - Wiley Online Library
Adaptive dynamic programming (ADP) methods have demonstrated their efficiency.
However, many of the applications for which ADP offers great potential, are also safety …

Online inverse reinforcement learning for nonlinear systems with adversarial attacks

B Lian, W Xue, FL Lewis, T Chai - International Journal of …, 2021 - Wiley Online Library
In the inverse reinforcement learning (RL) problem, there are two agents. A learner agent
seeks to mimic another expert agent's state and control input behavior trajectories by …

Barrier-critic adaptive robust control of nonzero-sum differential games for uncertain nonlinear systems with state constraints

C Qin, X Qiao, J Wang, D Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
In this article, for the nonzero-sum (NZS) differential games problem of uncertain nonlinear
systems with state constraints, an adaptive robust stabilization scheme based on the control …