Dota 2 with Large Scale Deep Reinforcement Learning. Berner, C., Brockman, G., Chan, B., Cheung, V., Dębiak, P., Dennison, C., Farhi, D., Fischer, Q., Hashme, S., & Hesse, C. arXiv preprint arXiv:1912.06680, 2019.
abstract   bibtex   
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 …
@Article{Berner2019,
author = {Berner, Christopher and Brockman, Greg and Chan, Brooke and Cheung, Vicki and Dębiak, Przemysław and Dennison, Christy and Farhi, David and Fischer, Quirin and Hashme, Shariq and Hesse, Chris}, 
title = {Dota 2 with Large Scale Deep Reinforcement Learning}, 
journal = {arXiv preprint arXiv:1912.06680}, 
volume = {}, 
number = {}, 
pages = {}, 
year = {2019}, 
abstract = {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 …}, 
location = {}, 
keywords = {}}

Downloads: 0