DeepMind’s new AI can perform more than 600 tasks, from playing video games to controlling robots

Gato is the name by which the new system of artificial intelligence (AI) from DeepMind, which has the ability to complete more than 600 different tasks, from writing image descriptions to controlling a robotic arm.

The system is a single generalist agent designed from the approach followed in large-scale language modeling. It has been trained with 604 different tasks and with different modalities, information that has been serialized in a flat series of tokens and processed with a neural network with the same weight for all tasks.

LOOK: Starlink: the comments for and against it receives in Chile and the US (and that we could soon hear in Peru)

“Cat samples the action vector autoregressively one token at a time. Once all the tokens that make up the action vector (as determined by the environment’s action specification) have been sampled, the action is decoded by reversing the tokenization procedure. This action is sent to the environment which gives way and produces a new observation. The procedure is repeated”, they explain in the text of the DeepMind study.

As a single generalist agent that can act as a vision and language model and perform actions in the real world. Cat understands the context and based on it decides whether to generate text, press a button or rotate a joint.

LOOK: Anonymous ‘hacks’ Russian YouTube and says it won’t work again

With this, an AI system capable of successfully performing tasks as varied as maintaining a chat conversation, controlling a robotic arm to stack blocks, writing the descriptions of images and playing Atari video games has been achieved.

DeepMind researchers have discussed with Gato the possibility of training an agent on a large number of tasks, and that this general agent “can be adapted with little additional data to be successful in an even greater number of tasks”.

Source: Elcomercio

Deshawn