Hybrid Reward Architecture
新闻与深度文章
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…
Reinforcement learning is about agents taking information from the world and learning a policy for interacting with it, so that they perform better. So, you can imagine a future where, every time you type on the keyboard, the keyboard learns…
If you’ve ever watched King of Kong: Fistful of Quarters, you know what a big deal it is to beat a video arcade game that was designed not to lose. Most humans can’t even come close. Enter Harm van Seijen,…
新闻报道 | TechCrunch
Microsoft’s AI beats Ms. Pac-Man
Microsoft subsidiary Maluuba used multiple individual AI agents to defeat the video game -- a long-time challenge for the AI and human community.
新闻报道 | 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.
新闻报道 | 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.
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…
A group of tech superheroes — also known as researchers at recent Microsoft acquisition Maluuba — have achieved the seeming impossible, and reached the maximum possible score on classic 1980s Atari game Ms. Pac-Man.
How defeating a classic 1982 videogame could help Microsoft make better enterprise software.