Google’s DeepMind AI can now play table tennis to a competitive level

[Pelican Press 0]

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

’s DeepMind AI can now play table tennis to a competitive level

Before artificial intelligence takes over the world, it seems it’ll beat us at table tennis first:

This is the hidden content, please

• Sign In
• or
• Sign Up

has reported on a ****** making use of its DeepMind AI that is now able to play ping-pong to an “******** human level” of performance.

The DeepMind lab is where

This is the hidden content, please

• Sign In
• or
• Sign Up

works on some of its most advanced AI tech, and we’ve previously seen plenty of practical DeepMind experiments: everything from AI adding audio to silent videos,  to discovering new materials.

In a new paper,

This is the hidden content, please

• Sign In
• or
• Sign Up

’s researchers say their table tennis ****** was able to win 13 out of 29 matches played against humans, with its success rate varying on the ability of the players it was competing with (from beginner to advanced).

“This is the first ****** agent capable of playing a sport with humans at human level and represents a milestone in ****** learning and control,” write the researchers, though they also say this is only a small step forward in the more general field of getting robots to perform useful, real world skills.

Not so fast

Demonstrations – Achieving human level competitive ****** table tennis –

This is the hidden content, please

• Sign In
• or
• Sign Up

data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///ywAAAAAAQABAAACAUwAOw==

This is the hidden content, please

• Sign In
• or
• Sign Up

Table tennis was chosen as a project by the

This is the hidden content, please

• Sign In
• or
• Sign Up

team because of the many different elements involved, from the complex motion physics to the hand-eye coordination that’s required to keep hitting the ball back successfully.

The ****** was trained by focusing on each particular type of shot separately, from backhand spin to forehand serve. This training was then combined with a more high-level algorithm designed to choose the necessary type of shot each time.

As you might expect, the ****** struggled most with faster shots (giving the AI less time to think about what to do), and the researchers are already thinking about how to improve the system – including how to make it more unpredictable in its play.

Sign up for breaking news, reviews, opinion, top tech deals, and more.

There’s even the built-in ability to learn from the strategies of the human opponent, and weigh up their strengths and weaknesses. The

This is the hidden content, please

• Sign In
• or
• Sign Up

is well worth a read if you’re interested in the challenges of AI training and scaling, and how robots might develop the combination of skills required to be useful in physical tasks.

You might also like

This is the hidden content, please

• Sign In
• or
• Sign Up

#Googles #DeepMind #play #table #tennis #competitive #level

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

For verified travel tips and real support, visit: https://hopzone.eu/