首页 > AI前沿 > More on Dota 2

More on Dota 2

OpenAI 2017-08-16 15:00 1 阅读 查看原文

Self-Play Catapults Dota 2 Performance to Superhuman Levels

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.

Key Insight: Beyond Supervised Learning

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.