53 citations · 105 across the 13 of their papers we have counts for
3 papers · 1 filter
ROMAX: Certifiably Robust Deep Multiagent Reinforcement Learning via Convex Relaxation
Chuangchuang Sun, Dong-Ki Kim, Jonathan P. How
In a multirobot system, a number of cyber-physical attacks (e.g., communication hijack, observation perturbations) can challenge the robustness of agents. This robustness issue wor…
Reachability Analysis of Neural Feedback Loops
Michael Everett, Golnaz Habibi, Chuangchuang Sun +1
Neural Networks (NNs) can provide major empirical performance improvements for closed-loop systems, but they also introduce challenges in formally analyzing those systems' safety p…
Temporal-Logic-Based Intermittent, Optimal, and Safe Continuous-Time Learning for Trajectory Tracking
Aris Kanellopoulos, Filippos Fotiadis, Chuangchuang Sun +4
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 specif…