
#45 - Building Dota Bots That Beat Pros - OpenAI's Greg Brockman, Szymon Sidor, and Sam Altman
Y Combinator Startup Podcast
00:00
Reactor Learning With Self-Play
We are using reinforcement learning with self-play. So essentially what's happening is we have a bot which observe some state in the environment and perform some actions based on that state. And then, you know, the bot gets feedback or whether it's doing good or not. And then tries to select the actions that yield to high, the positive feedback to high reward.
Transcript
Play full episode