The paper links to some YouTube videos of the AI in action:<p><a href="https://www.youtube.com/watch?v=oo0TraGu6QY&list=PLduGZax9wmiHg-XPFSgqGg8PEAV51q1FT" rel="nofollow">https://www.youtube.com/watch?v=oo0TraGu6QY&list=PLduGZax9wm...</a>
Video of the network actually playing deathmatch: <a href="https://www.youtube.com/watch?v=oo0TraGu6QY&index=1&list=PLduGZax9wmiHg-XPFSgqGg8PEAV51q1FT" rel="nofollow">https://www.youtube.com/watch?v=oo0TraGu6QY&index=1&list=PLd...</a>
Not end-to-end learning. They've included a lot of apriori information into their models to significantly constrain the search space. Maybe I'm being a little too harsh in my opinions, but with this work coming out of CMU I was expecting a little more.
I'm anxious to see if the sorts of networks that learned how to play Atari games could be taught to okay slither.io in the same way. I was interested in learning more about the sort of pathfinding challenges slither.io presents (safest path to large food reward with moving obstacles) and started to peel apart some JavaScript "bots" and realized they're doing some basic math that's not able to outperform a human. I wanted to make an iOS version of slither.io whose AI snakes for offline play did better than the current official app, but I don't know enough about the topic to dive into the deep end of it.<p>So if anyone has pointers on getting started with something like this for a game not already configured for the "gym" used by many current networks playing games, I'd love to hear more!