Well, the title says it all really.. This is something I did for an interview for a pretty prestigious AI company in London, specialising in deep reinforcement learning, acquired by Google for $500M a few years ago.. I really shouldn’t say more.. Oh, yeah, they also came up AlphaGo..
Unfortunately, I didn’t get the job, but it was a really engaging and fun exercise so I figured I might as well share it. Here’s the repo.