{"id":447303,"date":"2017-12-06T09:36:31","date_gmt":"2017-12-06T17:36:31","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?p=447303"},"modified":"2023-05-01T12:06:15","modified_gmt":"2023-05-01T19:06:15","slug":"hybrid-reward-architecture-fall-ms-pac-man-dr-harm-van-seijen","status":"publish","type":"post","link":"https:\/\/www.microsoft.com\/en-us\/research\/podcast\/hybrid-reward-architecture-fall-ms-pac-man-dr-harm-van-seijen\/","title":{"rendered":"Hybrid Reward Architecture and the Fall of Ms. Pac-Man with Dr. Harm van Seijen"},"content":{"rendered":"\n
\"photo<\/a><\/figure>\n\n\n\n

Episode 3 | December 6, 2017<\/h2>\n\n\n\n

Hybrid Reward Architecture and the Fall of Ms. Pac-Man with Dr. Harm van Seijen<\/strong><\/p>\n\n\n\n

If you\u2019ve 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\u2019t even come close. Enter Harm van Seijen, and a team of machine learning researchers from Microsoft Research Montreal<\/a>. They took on Ms. Pac-man. And won. Today we\u2019ll talk to Harm about his work in reinforcement learning, the inspiration for hybrid reward architecture, visit a few islands of tractability and get an inside look at the science behind the AI defeat of one of the most difficult video arcade games around.<\/p>\n\n\n\n

To find out more about Harm van Seijen and the groundbreaking work going on at Microsoft Research Montreal<\/a>, visit Microsoft.com\/research.<\/a><\/p>\n\n\n\n

\n\t
\n\t\t

\n\t\t\tSubscribe to the Microsoft Research Podcast<\/a>:\t\t<\/h2>\n\t\t