[1912.06680] Dota 2 with Large Scale Deep Reinforcement Learning

[1912.06680] Dota 2 with Large Scale Deep Reinforcement Learning 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

 
 
 
 
 

 
 
 
 
 
--> 

 
 
 Computer Science > Machine Learning

 

 
 arXiv:1912.06680 (cs)
 
 
 
 
 
 [Submitted on 13 Dec 2019] 
 Title: Dota 2 with Large Scale Deep Reinforcement Learning

 Authors: OpenAI : Christopher Berner , Greg Brockman , Brooke Chan , Vicki Cheung , Przemysław Dębiak , Christy Dennison , David Farhi , Quirin Fischer , Shariq Hashme , Chris Hesse , Rafal Józefowicz , Scott Gray , Catherine Olsson , Jakub Pachocki , Michael Petrov , Henrique P. d.O. Pinto , Jonathan Raiman , Tim Salimans , Jeremy Schlatter , Jonas Schneider , Szymon Sidor , Ilya Sutskever , Jie Tang , Filip Wolski , Susan Zhang View a PDF of the paper titled Dota 2 with Large Scale Deep Reinforcement Learning, by OpenAI: Christopher Berner and 24 other authors 
 View PDF 

 
 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.
 

 
 
 
 Subjects: 
 
 Machine Learning (cs.LG) ; Machine Learning (stat.ML) 
 
 Cite as: 
 arXiv:1912.06680 [cs.LG] 
 
 
 
 (or 
 arXiv:1912.06680v1 [cs.LG] for this version)
 
 
 
 
 https://doi.org/10.48550/arXiv.1912.06680 
 
 
 Focus to learn more 
 
 
 
 arXiv-issued DOI via DataCite 
 
 
 
 
 
 
 
 Submission history

 From: Filip Wolski [ view email ] 
 [v1] 
 Fri, 13 Dec 2019 19:56:40 UTC (8,625 KB)

 
 
 
 
 
 Full-text links: 
 Access Paper:

 
 
View a PDF of the paper titled Dota 2 with Large Scale Deep Reinforcement Learning, by OpenAI: Christopher Berner and 24 other authors View PDF 
 TeX Source
 
 
 view license 
 
 
 Current browse context: cs.LG 

 
 
 < prev 
 
 | 
 next > 
 

 
 new 
 | 
 recent 
 | 2019-12 
 
 Change to browse by:
 
 cs 
 stat 
 stat.ML 
 
 

 
 
 References & Citations

 
 NASA ADS 
 Google Scholar 

 Semantic Scholar 

 
 
 

 
 
 2 blog links 

 ( what is this? )
 
 
 
 DBLP - CS Bibliography

 
 listing | bibtex 
 
 Greg Brockman 
 Vicki Cheung 
 Christopher Hesse 
 Rafal Józefowicz 
 Scott Gray &hellip; 
 
 
 export BibTeX citation 
 Loading... 
 

 
 
 
 BibTeX formatted citation

 &times; 
 
 
 loading... 
 
 
 Data provided by: 
 
 
 
 
 Bookmark

 
 
 
 
 
 
 
 
 
 
 
 Bibliographic Tools 
 
 Bibliographic

... (truncated, 5 KB total)