4 citations · 7 across the 4 of their papers we have counts for
6 papers
Assured Learning-enabled Autonomy: A Metacognitive Reinforcement Learning Framework
Aquib Mustafa, Majid Mazouchi, Subramanya Nageshrao +1
Reinforcement learning (RL) agents with pre-specified reward functions cannot provide guaranteed safety across variety of circumstances that an uncertain system might encounter. To…
A Convex Programming Approach to Data-Driven Risk-Averse Reinforcement Learning
Yuzhen Han, Majid Mazouchi, Subramanya Nageshrao +1
This paper presents a model-free reinforcement learning (RL) algorithm to solve the risk-averse optimal control (RAOC) problem for discrete-time nonlinear systems. While successful…
A Satisficing Control Design Framework with Safety and Performance Guarantees for Constrained Systems under Disturbances
Yuzhen Han, Hamidreza Modares
This paper presents a safe robust policy iteration (SR-PI) algorithm to design controllers with satisficing (good enough) performance and safety guarantee. This is in contrast to s…
Adaptive Finite-time Disturbance Rejection for Nonlinear Systems using an Experience-Replay based Disturbance Observer
Zhitao Li, Amin Vahidi-Moghaddam, Hamidreza Modares +1
Control systems are inevitably affected by external disturbances, and a major objective of the control design is to attenuate or eliminate their adverse effects on the system perfo…
Data-driven Dynamic Multi-objective Optimal Control: An Aspiration-satisfying Reinforcement Learning Approach
Majid Mazouchi, Yongliang Yang, Hamidreza Modares
This paper presents an iterative data-driven algorithm for solving dynamic multi-objective (MO) optimal control problems arising in control of nonlinear continuous-time systems. It…
Resilient Synchronization of Distributed Multi-agent Systems under Attacks
Aquib Mustafa, Rohollah Moghadam, Hamidreza Modares
In this paper, we first address adverse effects of cyber-physical attacks on distributed synchronization of multi-agent systems, by providing conditions under which an attacker can…