Hacker News Reader

Had the same thought. :) I wonder if anyone has done a challenge using that game which has simpler inputs I believe?

Simplest RL algorithm (Q-learning) achieves 100m in QWOP: https://www.youtube.com/watch?v=e27TUmMkOA0

Although it found and exploited a local maximum of "knee scraping" technique (which humans can replicate) :)