Dota 2 with Large Scale Deep Reinforcement Learning

12/13/2019 ∙ by OpenAI, et al. ∙ 13

On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions at an esports game. The game of Dota 2 presents novel challenges for AI systems such as long time horizons, imperfect information, and complex, continuous state-action spaces, all challenges which will become increasingly central to more capable AI systems. OpenAI Five leveraged existing reinforcement learning techniques, scaled to learn from batches of approximately 2 million frames every 2 seconds. We developed a distributed training system and tools for continual training which allowed us to train OpenAI Five for 10 months. By defeating the Dota 2 world champion (Team OG), OpenAI Five demonstrates that self-play reinforcement learning can achieve superhuman performance on a difficult task.



There are no comments yet.


page 36

page 37

page 39

page 41

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.