Scaling The “Wrong” Algorithm
8:42–9:27 · 46s
They pursued Dota to replace flawed PPO, but simply scaling it beat top humans—revealing massive compute plus simple methods can win.
8:42–9:27 · 46s
They pursued Dota to replace flawed PPO, but simply scaling it beat top humans—revealing massive compute plus simple methods can win.
We use cookies to understand how you use our platform and to improve your experience. Click "Accept All" to consent, or "Decline non-essential" to opt out of non-essential cookies. Read our Privacy Policy.