AI made from jelly learns to play Pong – and is getting better and better

AI Pong, Artificial Intelligence, Science, Study, Research, Research Paper, University of Reading, Jelly, Video Game, Video Game, Memory

A team of researchers from England has taught a non-biological AI material to play Pong. However, the jelly can’t just run the video game. Over time it gets better and better.

Science has been interested in teaching other life forms the game of “Pong” using artificial intelligence for years. A famous example of this is Elon Musk. A few years ago, his company Neuralink released a video showing a monkey controlling the video game using an implanted chip.

Researchers from the Australian start-up Cortical Labs have already taught a silicon chip based on human brain cells to play pong. Now scientists from the English University of Reading also tried it. A team led by Yoshikatsu Hayashi wanted to new study find out whether a non-biological material can also play pong. The result: It can. And not only that: AI is actually getting better and better at it.

Memory made of jelly: AI learns to play Pong

Hayashi and his team used a hydrogel for the study. This is a jelly-like material that is used for a variety of applications, such as components for soft robots.

The hydrogel contains charged particles called ions. Through electrical stimulation, they move through the material and pull water molecules with them. This changes the shape of the jelly. This change in the distribution of the ions influences the next arrangement of the particles, explains Hayashi. “It’s like a physical memory.”

To test whether this “memory” could make the hydrogel play Pong, the researchers used electrodes. In this way, they combined the material with a computer. The game itself is divided into a grid of six squares, corresponding to six pairs of electrodes. Each time the ball moved through one of the squares, the corresponding electrodes sent an electrical signal to the hydrogel, causing the ions to change position.

See also  The Future of Executive Coaching: How AI Improves, Rather Than Replaces, Human Insight

The sensor electrodes then measured the electrical current of the rearranged ions and passed this information back to the computer, which interpreted it as a command: it moved the game paddle to a new position. Over time, a fundamental memory was formed in this way, as the movement of the ions was influenced by their previous rearrangements.

Jelly AI continued to improve

First, the hydrogel only hit the ball about half the time. After about 24 minutes, however, the hit rate increased to 60 percent. This suggests that the material can update its “memory” for the ball’s movement based on the ion pattern. The improved performance also led to longer rallies.

The research team conducted control experiments in which they fed the material false information about the ball’s position or didn’t stimulate it at all. Under these conditions, the hydrogel’s Pong game showed no signs of improvement. This gave rise to the assumption that it will only get better if it is fed the right information.

“More work needs to be done”

Pong did not master the material from the English research group as quickly as DishBrain. However, this is because hydrogel is a much simpler system, says Hayashi. Nevertheless, the results show that it has further computing capabilities. Scientists could use these to develop more efficient algorithms.

Brett Kagan from Cortical Labs also commented favorably on the new study. It’s a first step toward demonstrating that synthetic materials can use a basic form of “memory” to improve performance, he explains. “The system demonstrates memory in a similar way that a riverbed records the memory of a river.”

The authors from England tried a creative approach to transfer concepts from neuroscience to a more physically based system, Kagan continued. However, more work needs to be done in the future.

The video game Pong has been around since the 1970s and is considered an absolute classic. The principle is simple: the players control a vertical or horizontal line and have to hit a virtual tennis ball back and forth.

See also  Graphite trick: New electric car battery can be charged in 15 minutes

Also interesting:

  • Study: AI cannot learn continuously – training always starts from zero
  • Self-healing power grid: Artificial intelligence should prevent blackouts
  • Study shows: Google is throttling its AI search results
  • How does a hybrid car actually work?

The post AI from jelly learns to play pong – and is getting better and better by Beatrice Bode first appeared on BASIC thinking. Follow us too Facebook, Twitter and Instagram.



As a Tech Industry expert, I find the concept of AI made from jelly learning to play Pong fascinating and exciting. This innovative approach to developing artificial intelligence showcases the endless possibilities of merging different technologies to create something truly unique.

The fact that the AI is getting better and better at playing Pong demonstrates the power of machine learning and neural networks in improving performance over time. It also highlights the adaptability and learning capabilities of AI, even when it is created from unconventional materials like jelly.

This advancement in AI technology opens up new avenues for research and development in the field of artificial intelligence. It shows that AI can be created in various forms and still exhibit impressive learning and problem-solving abilities.

Overall, the idea of jelly-based AI mastering Pong is a testament to the limitless potential of AI and its ability to continuously evolve and improve. It is a promising glimpse into the future of AI technology and its applications in various industries.

Credits