@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 = {}}

{"_id":"8g9HbiwDRD2XJkGqX","bibbaseid":"berner-brockman-chan-cheung-dbiak-dennison-farhi-fischer-etal-dota2withlargescaledeepreinforcementlearning-2019","authorIDs":[],"author_short":["Berner, C.","Brockman, G.","Chan, B.","Cheung, V.","Dębiak, P.","Dennison, C.","Farhi, D.","Fischer, Q.","Hashme, S.","Hesse, C."],"bibdata":{"bibtype":"article","type":"article","author":[{"propositions":[],"lastnames":["Berner"],"firstnames":["Christopher"],"suffixes":[]},{"propositions":[],"lastnames":["Brockman"],"firstnames":["Greg"],"suffixes":[]},{"propositions":[],"lastnames":["Chan"],"firstnames":["Brooke"],"suffixes":[]},{"propositions":[],"lastnames":["Cheung"],"firstnames":["Vicki"],"suffixes":[]},{"propositions":[],"lastnames":["Dębiak"],"firstnames":["Przemysław"],"suffixes":[]},{"propositions":[],"lastnames":["Dennison"],"firstnames":["Christy"],"suffixes":[]},{"propositions":[],"lastnames":["Farhi"],"firstnames":["David"],"suffixes":[]},{"propositions":[],"lastnames":["Fischer"],"firstnames":["Quirin"],"suffixes":[]},{"propositions":[],"lastnames":["Hashme"],"firstnames":["Shariq"],"suffixes":[]},{"propositions":[],"lastnames":["Hesse"],"firstnames":["Chris"],"suffixes":[]}],"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":"","bibtex":"@Article{Berner2019,\nauthor = {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}, \ntitle = {Dota 2 with Large Scale Deep Reinforcement Learning}, \njournal = {arXiv preprint arXiv:1912.06680}, \nvolume = {}, \nnumber = {}, \npages = {}, \nyear = {2019}, \nabstract = {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 …}, \nlocation = {}, \nkeywords = {}}\n\n\n","author_short":["Berner, C.","Brockman, G.","Chan, B.","Cheung, V.","Dębiak, P.","Dennison, C.","Farhi, D.","Fischer, Q.","Hashme, S.","Hesse, C."],"key":"Berner2019","id":"Berner2019","bibbaseid":"berner-brockman-chan-cheung-dbiak-dennison-farhi-fischer-etal-dota2withlargescaledeepreinforcementlearning-2019","role":"author","urls":{},"downloads":0},"bibtype":"article","biburl":"https://gist.githubusercontent.com/stuhlmueller/a37ef2ef4f378ebcb73d249fe0f8377a/raw/6f96f6f779501bd9482896af3e4db4de88c35079/references.bib","creationDate":"2020-01-27T02:13:33.777Z","downloads":0,"keywords":[],"search_terms":["dota","large","scale","deep","reinforcement","learning","berner","brockman","chan","cheung","dębiak","dennison","farhi","fischer","hashme","hesse"],"title":"Dota 2 with Large Scale Deep Reinforcement Learning","year":2019,"dataSources":["hEoKh4ygEAWbAZ5iy"]}