Robin Kahlow
Machine learning, games and web experiments. Lately: reinforcement learning in the real Warcraft III.
Latest post
18 October 2026
Beating Warcraft III's insane AI with self-play reinforcement learning on one desktop
In three weeks, an agent that plays the real Warcraft III went from losing to the easy AI to winning about nine games in ten against insane, trained by self-play on one desktop.
Read the post →