Add to Favourites
To login click here
Nvidia has developed a new AI training system called Eureka that uses OpenAI’s GPT-4 large language model (LLM) to train robots to perform tasks faster than is standard. Eureka is able to teach a robotic hand to flawlessly execute complex pen-spinning tricks and other tasks such as juggling, using scissors, and opening and closing doors. The AI agents leverage advanced reinforcement learning to automatically generate training programs that enable robots to master intricate real-world skills. Eureka’s key innovation is its ability to automatically generate optimized “reward” programs defining criteria for trial-and-error robotic learning, removing the need for human experts to manually formulate reinforcement learning goals.