DeepMind researchers develop method to efficiently teach robots tasks like grasping
Source: venturebeat.com In a paper published this week on the preprint server Arxiv.org, scientists at DeepMind introduce the idea of simple sensor intentions (SSIs), a way to reduce the knowledge needed to define rewards (functions describing how AI ought to behave) in reinforcement learning systems. They claim that SSIs can help to solve a range of complex robotic tasks Read More