One step closer to the Matrix: AI defeats human champion in Street Fighter — with a revolutionary type of memory it uses to make itself even more powerful
The AI system, powered by phase-change memory and reinforcement learning, was trained for just two days
When you purchase through links on our site, we may earn an affiliate commission.Here’s how it works.
Researchers from the Singapore University of Technology and Design (SUTD) created a new software centered around reinforcement learning and phase-change memory that’s designed to understand complicated movement design.
Previous work has applied this kind of deep learning to other games like Chess or Go, but they decided instead to expose the D-PPO algorithm to the rigors of Street Fighter Champion Edition II. The SUTD researchers trained its SF-R2 AI player on two days of consecutive play against the computer, before letting it loose on a human participant – who the AI-powered system beat comfortably.
The work has implications for movement science more broadly, according to theresearch paper, and can possibly be fed into improving robotics and autonomous vehicles, for example. It paves the way for broadly applicable training in fields where machines may observe human norms and attempt to replicate and outperform them.
Ready Pl-AI-yer One
One of the major milestones that AI researchers have used to measure the effectiveness of the systems they’ve built is by letting them compete with human players in different kinds of games. This has been happening for some time.
In 2017, anAlpha Go AI built by DeepMind beat the number-one human Go playerin the world for the second time, following thefirst victory over Fan Huithe previous year.Microsoft’s AI, in June, achievedthe world’s first perfect Ms. Pac-Manscore, and in August we saw anOpenAI engine beating the best Dota 2 playersof the time.
This latest milestone – besting a Street Fighter champion – was made possible due to reinforcement learning as well as phase-change memory. First developed byHP, this is a form of nonvolatile memory achieved by using electrical charges to change areas on chalcogenide glass. It’s much faster than commonly used Flash memory.
“Our approach is unique because we use reinforcement learning to solve the problem of creating movements that outperform those of top human players,” said principal investigator Desmond Loke toTechXplore. “This was simply not possible using prior approaches, and it has the potential to transform the types of moves we can create.
Are you a pro? Subscribe to our newsletter
Sign up to the TechRadar Pro newsletter to get all the top news, opinion, features and guidance your business needs to succeed!
More from TechRadar Pro
Keumars Afifi-Sabet is the Technology Editor for Live Science. He has written for a variety of publications including ITPro, The Week Digital and ComputerActive. He has worked as a technology journalist for more than five years, having previously held the role of features editor with ITPro. In his previous role, he oversaw the commissioning and publishing of long form in areas including AI, cyber security, cloud computing and digital transformation.
Cisco issues patch to fix serious flaw allowing possible industrial systems takeover
7 myths about email security everyone should stop believing
Your doctor may have an AI assistant taking notes during your next Zoom call
