News & features
Research Collection – Shall we play a game?
From a research point of view, games offer an amazing environment in which to develop new machine learning algorithms and techniques. And we hope, in due course, that those new algorithms will feed back not just into gaming, but into…
Reliability in Reinforcement Learning
| Romain Laroche
Reinforcement Learning (RL), much like scaling a 3,000-foot rock face, is about learning to make sequential decisions. The list of potential RL applications is expansive, spanning robotics (drone control), dialogue systems (personal assistants, automated call centers), the game industry (non-player…
In the news | The AI Blog
Divide and conquer: How Microsoft researchers used AI to master Ms. Pac-Man
Microsoft researchers have created an artificial intelligence-based system that learned how to get the maximum score on the addictive 1980s video game Ms. Pac-Man, using a divide-and-conquer method that could have broad implications…
In the news | BBC News
Microsoft AI plays a perfect game of Ms Pac-Man
One of Microsoft’s artificial intelligence systems has conquered the 1980s video game Ms. Pac-Man. The team, from Microsoft-owned Canadian AI firm Maluuba, achieved the perfect score of 999,990.
In the news | PCMag India
Microsoft AI first to reach perfect Ms Pac-Man score
Researchers at Maluuba, a deep-learning startup recently acquired by Microsoft, have developed an artificial intelligence (AI) system that became the first player ever to achieve a perfect 999,990 score in Ms Pac-Man — an arcade video game.
In the news | TechCrunch
Microsoft’s AI beats Ms. Pac-Man
The complexity of Ms. Pac-Man, with its many boards and moving parts, has made the classic title an especially difficult target. Until now, no human or machine has achieved the feat.
Hybrid Reward Architecture (HRA) Achieving super-human performance on Ms. Pac-Man
Games are popular as a test-bed for new machine learning techniques because they can be very challenging and allow for easy analysis of new learning techniques in a controlled environment. For reinforcement learning, where the goal is to learn good…
In the news | The Verge
Sorry humans, Microsoft’s AI is the first to reach a perfect Ms. Pac-Man score
Sorry humans, Microsoft’s AI is the first to reach a perfect Ms. Pac-Man score. AI researchers have a documented penchant for using video games to test machine learning.
In the news | Mashable
An AI just beat ‘Ms. Pac-Man.’ We’re doomed.
Ms. Pac-Man was supposed to be the more difficult arcade game. But now it’s been laid low — like chess, Go, and poker before it — by artificial intelligence. Researchers with deep learning company Maluuba, which Microsoft acquired earlier this…