From 0–22 to 0–5: Learning AI the Hard Way in 1999
In 1999, three of us at HKUST decided to spend our final year project trying to teach a team of simulated soccer players how to survive against the world champions. We did not have GPUs, Python, or deep learning frameworks. We had C, a room full of Sun workstations, an NFS share, and a lot of stubbornness. Our opponent was CMUnited from Carnegie Mellon University, the top RoboCup simulator team at the time. They were the kind of team that routinely crushed others by double digits. Our starting point was simple: take our baseline HKUST team, play them against CMUnited, and see what happens. ...