Temporal-Logic-Based Intermittent, Optimal, and Safe Continuous-Time Learning for Trajectory Tracking

no code implementations • 6 Apr 2021 • Aris Kanellopoulos, Filippos Fotiadis, Chuangchuang Sun, Zhe Xu, Kyriakos G. Vamvoudakis, Ufuk Topcu, Warren E. Dixon

In this paper, we develop safe reinforcement-learning-based controllers for systems tasked with accomplishing complex missions that can be expressed as linear temporal logic specifications, similar to those required by search-and-rescue missions.

Reinforcement Learning (RL) Safe Reinforcement Learning

A Multi-step and Resilient Predictive Q-learning Algorithm for IoT with Human Operators in the Loop: A Case Study in Water Supply Networks

no code implementations • 6 Jun 2020 • Maria Grammatopoulou, Aris Kanellopoulos, Kyriakos G. ~Vamvoudakis, Nathan Lau

We consider the problem of recommending resilient and predictive actions for an IoT network in the presence of faulty components, considering the presence of human operators manipulating the information of the environment the agent sees for containment purposes.

Q-Learning Scheduling