Dark Reading

'God-Like' Attack Machines: AI Agents Ignore Security Policies

Any AI agent will go above and beyond to complete assigned tasks, even breaking through their carefully designed guardrails.
GitHub

[ICRA 2026] KINESIS: Reinforcement Learning-Based Motion Imitation for Physiologically Plausible Musculoskeletal Motor Control

KINESIS is a model-free imitation-learning framework that facilitates the development of effective and scalable muscle-based control policies of locomotion. KINESIS is trained on 1.8 hours of ...
IEEE

Audio-Driven Reinforcement Learning for Head-Orientation in Naturalistic Environments

Abstract: Although deep reinforcement learning (DRL) approaches in audio signal processing have seen substantial progress in recent years, fully audio-driven DRL for tasks such as navigation, gaze ...
IEEE

Environment-Tolerant Trust Opportunity Routing Based on Reinforcement Learning for Internet of Underwater Things

Abstract: The Internet of Underwater Things (IoUT) has garnered significant interest due to its potential applications in monitoring underwater environments. However, the unique characteristics of ...