Here’s another great Two Minute Papers video on DeepMind’s venture into computer vision.
In this YouTube video, Siraj Raval goes through the steps necessary to install and run the StarCraft II Environment that DeepMind recently open-sourced!
He gets into DeepMind’s Reinforcement Learning history, the configuration steps, and then runs a pre-trained Deep Q model at the end that will complete a the shard collection mini-game.
Two Minute Papers has a great video focusing on how DeepMind taught itself how to walk all by itself. It’s a great look at the impact of reinforcement learning.
The paper referenced in the video “Emergence of Locomotion Behaviours in Rich Environments” is available online.