Dota 2 with Large Scale Deep Reinforcement Learning
OpenAI, :, Christopher Berner, Greg Brockman, Brooke Chan, Vicki Cheung, Dębiak, Przemysław, Christy Dennison, David Farhi, Quirin Fischer, Shariq Hashme, Hesse, Chris, Rafał Józefowicz, Scott Gray, Catherine Olsson, Jakub Pachocki, Michael Petrov, Pinto, Henrique P. d. O., Jonathan Raiman, Tim Salimans · arXiv (Cornell University) · 2019
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.