%0 Generic %1 openai2019large %A OpenAI, %A :, %A Berner, Christopher %A Brockman, Greg %A Chan, Brooke %A Cheung, Vicki %A Dębiak, Przemysław %A Dennison, Christy %A Farhi, David %A Fischer, Quirin %A Hashme, Shariq %A Hesse, Chris %A Józefowicz, Rafal %A Gray, Scott %A Olsson, Catherine %A Pachocki, Jakub %A Petrov, Michael %A Pinto, Henrique P. d. O. %A Raiman, Jonathan %A Salimans, Tim %A Schlatter, Jeremy %A Schneider, Jonas %A Sidor, Szymon %A Sutskever, Ilya %A Tang, Jie %A Wolski, Filip %A Zhang, Susan %D 2019 %K %T Dota 2 with Large Scale Deep Reinforcement Learning %U http://arxiv.org/abs/1912.06680 %X 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.

@misc{openai2019large, 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 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.}, added-at = {2023-08-25T05:53:25.000+0200}, author = {OpenAI and : and 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 and Józefowicz, Rafal and Gray, Scott and Olsson, Catherine and Pachocki, Jakub and Petrov, Michael and Pinto, Henrique P. d. O. and Raiman, Jonathan and Salimans, Tim and Schlatter, Jeremy and Schneider, Jonas and Sidor, Szymon and Sutskever, Ilya and Tang, Jie and Wolski, Filip and Zhang, Susan}, biburl = {https://www.bibsonomy.org/bibtex/2b945e7512766e1ca33664248d4596896/desplode}, interhash = {d176f9c00b2ce62b3e1d8398e18187bf}, intrahash = {b945e7512766e1ca33664248d4596896}, keywords = {}, note = {cite arxiv:1912.06680}, timestamp = {2023-08-25T05:53:25.000+0200}, title = {Dota 2 with Large Scale Deep Reinforcement Learning}, url = {http://arxiv.org/abs/1912.06680}, year = 2019 }