Scientists at Tinkoff Research have developed a new method for training artificial intelligence (AI) that is much faster and more efficient than existing methods.
This new method, called SAC-RND, makes it possible to train robots 20 times faster and 10% better than other methods. They tested this on robotic simulators and got impressive results.
This algorithm can be useful for improving the safety of unmanned vehicles, simplifying logistics, speeding up delivery, optimizing energy processes and reducing harmful emissions. This also brings us closer to the creation of versatile robots that can perform a variety of tasks.
Research into this new method was celebrated by the global scientific community and presented at the International Conference on Machine Learning (ICML), along with articles from Google, Amazon, Sony and other leading companies.
This news refutes the previous thought that Random Neural Networks (RNDs) are not suitable for training robots. Scientists from Tinkoff Research have optimized this method, making it the most effective.
Tinkoff Research actively explores various areas of artificial intelligence such as natural language processing, computer vision, reinforcement learning, and recommendation systems. His work is recognized in the scientific community and cited by other scientists, including Google and DeepMind.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
