OpenAI Blog · Aug 16, 2017
More on Dota 2
Reviewed by Errol Vogt, Site support technician & online learning analyst · original summary · editorial policy
More on Dota 2. Our Dota 2 result shows that self-play can catapult the performance of machine learning systems from far below human level to superhuman, given sufficient compute. In the span of a month, our system went from barely matching a high-ranked player to beating the top pros and has continued to improve since then. Supervised deep learning systems can only be as good as their training datasets, but in self-play systems, the available data improves automatically as the agent gets better. This update is relevant for small-office operators tracking changes in their tools.
Operator takeaway: For operators: review whether 'More on Dota 2' affects your current setup before relying on it in production.
ai phone