AdverSAR: Adversarial Search and Rescue via Multi-Agent Reinforcement Learning

no code implementations • 20 Dec 2022 • Aowabin Rahman, Arnab Bhattacharya, Thiagarajan Ramachandran, Sayak Mukherjee, Himanshu Sharma, Ted Fujimoto, Samrat Chatterjee

Search and Rescue (SAR) missions in remote environments often employ autonomous multi-robot systems that learn, plan, and execute a combination of local single-robot control actions, group primitives, and global mission-oriented coordination and collaboration.

Meta-Learning Multi-agent Reinforcement Learning +2

Optimization-Based Resiliency Verification in Microgrids via Maximal Adversarial Set Characterization

no code implementations • 28 Mar 2022 • Nawaf Nazir, Thiagarajan Ramachandran, Saptarshi Bhattacharya, Ankit Singhal, Soumya Kundu, Veronica Adetola

An inner-approximation of the set of adversarial events which can be mitigated by the available flexibility is constructed using an optimization based approach.

Automated Adversary Emulation for Cyber-Physical Systems via Reinforcement Learning

no code implementations • 9 Nov 2020 • Arnab Bhattacharya, Thiagarajan Ramachandran, Sandeep Banik, Chase P. Dowling, Shaunak D. Bopardikar

Adversary emulation is an offensive exercise that provides a comprehensive assessment of a system's resilience against cyber attacks.

reinforcement-learning Reinforcement Learning (RL)