Tag

Deep Reinforcement Learning

All articles tagged with #deep reinforcement learning

"AI Breakthrough: Overcoming Fusion Plasma Instability for Near-Unlimited Clean Energy"

Originally Published 1 year ago — by Nature.com

Nuclear fusion experiments in tokamaks have achieved significant success, but plasma disruption due to tearing instability remains a critical issue. To address this, researchers have developed an AI-based tearing-avoidance system using deep reinforcement learning (RL) to actively control the beam power and plasma shape in real time, maintaining low tearability and high plasma pressure. Experiments at the DIII-D tokamak demonstrated the system's ability to avoid disruptive tearing instability, showcasing the potential for AI-accelerated real-time instability-avoidance techniques in fusion energy research.

science science-and-technology deep-reinforcement-learning nuclear-fusion plasma-control-system science-and-technology tearing-instability tokamak

MIT's Maverick Approach to Safe and Reliable AI Autopilots.

Originally Published 2 years ago — by SciTechDaily

MIT researchers have developed an AI-based method to improve safety and stability in autonomous robots, successfully addressing the ‘stabilize-avoid’ problem. Using a two-step approach involving deep reinforcement learning and mathematical optimization, the method was effectively tested on a simulated jet aircraft. This could have future applications in dynamic robots requiring safety and stability, like autonomous delivery drones.

science ai ai autonomous-robots deep-reinforcement-learning mathematical-optimization mit safety-and-stability