EurekAlert!

A new AI-based attack framework advances multi-agent reinforcement learning by amplifying vulnerability and bypassing defenses

Researchers have developed a novel framework, termed PDJA (Perception–Decision Joint Attack), that leverages artificial ...
Nature

Multi-Agent Reinforcement Learning

Multi-Agent Reinforcement Learning (MARL) is an emerging subfield of artificial intelligence that investigates how multiple autonomous agents can learn collaboratively and competitively within an ...
Nature

Reimagining Teaching and Learning in the Age of Generative AI Agents

This collection supports and amplifies research related to SDG 4: Quality Education. Generative AI is transforming the conventional dyadic teacher-student dynamic into a triadic framework centered ...
EurekAlert!

MA3C: Enhancing communication robustness in multi-agent learning through adaptable auxiliary multi-agent adversary generation

The overall relationship between the attacker and the ego system. The black solid arrows indicate the direction of data flow, the red solid ones indicate the direction of gradient flow and the red ...
Campus Technology

Microsoft Intros Open Source Multi-Agent AI System

Microsoft researchers have unveiled a new open source multi-agent AI system, aimed to help enterprises automate complex tasks typically requiring human intervention. Named Magnetic-One, the project is ...