Adversarial Multi

Adversarial multi-agent systems research focuses on developing robust and efficient algorithms for multi-agent interactions where some agents may act maliciously or unexpectedly. Current research emphasizes developing resilient decision-making frameworks, often employing reinforcement learning and diffusion models, to handle uncertainties stemming from adversarial actions or noisy observations, particularly in robotics and security applications. This work is crucial for improving the reliability and safety of autonomous systems operating in complex, unpredictable environments, addressing challenges such as adversarial attacks on deep learning models and the need for secure communication in multi-robot teams. The ultimate goal is to create systems that can maintain performance and achieve objectives even under adversarial conditions.

Papers

March 16, 2024

Diffusion-Reinforcement Learning Hierarchical Motion Planning in Adversarial Multi-agent Games
Zixuan Wu, Sean Ye, Manisha Natarajan, Matthew C. Gombolay
Reinforcement Learning Motion Planning Diffusion Planner Pursuit Evasion Adversarial Multi

February 6, 2024

Adversarial Robots as Creative Collaborators
Shayla Lee, Wendy Ju
Sustained Creativity Creative Task Creative Practice Robotic Drawing Adversarial Multi

August 1, 2023

Kidnapping Deep Learning-based Multirotors using Optimized Flying Adversarial Patches
Pia Hanfeld, Khaled Wahba, Marina M. -C. Höhne, Michael Bussmann, Wolfgang Hönig
Adversarial Attack Adversarial Patch Diving Deep Adversarial Multi

July 18, 2023

VISER: A Tractable Solution Concept for Games with Information Asymmetry
Jeremy McMahan, Young Wu, Yudong Chen, Xiaojin Zhu, Qiaomin Xie
Self Supervised Video Game Markov Game Information Asymmetry Moral Tractability Approximate Equilibrium Adversarial Multi

March 7, 2023

Exploiting Trust for Resilient Hypothesis Testing with Malicious Robots (evolved version)
Matthew Cavorsi, Orhan Eren Akgün, Michal Yemini, Andrea Goldsmith, Stephanie Gil
Hypothesis Testing Version Identification Trust Inference Adversarial Multi

December 20, 2022

AdverSAR: Adversarial Search and Rescue via Multi-Agent Reinforcement Learning
Aowabin Rahman, Arnab Bhattacharya, Thiagarajan Ramachandran, Sayak Mukherjee, Himanshu Sharma, Ted Fujimoto, Samrat Chatterjee
Multi Agent Reinforcement Learning Search and Rescue Multi Robot Team Monotone Adversary Adversarial Search Adversarial Multi Adversarial Communication

December 6, 2022

What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?
Songyang Han, Sanbao Su, Sihong He, Shuo Han, Haizhao Yang, Shaofeng Zou, Fei Miao
Multi Agent Reinforcement Learning Solution Path Robust Policy Sub Optimal Robust Agent Adversarial Multi Adversarial Team Game

September 25, 2022

Exploiting Trust for Resilient Hypothesis Testing with Malicious Robots
Matthew Cavorsi, Orhan Eren Akgün, Michal Yemini, Andrea Goldsmith, Stephanie Gil
Hypothesis Testing Trust Inference Adversarial Multi

April 15, 2022

Revisiting the Adversarial Robustness-Accuracy Tradeoff in Robot Learning
Mathias Lechner, Alexander Amini, Daniela Rus, Thomas A. Henzinger
Adversarial Attack Adversarial Training Robot Learning Accuracy Robustness Adversarial Multi