papers AI Learner
The Github is limit! Click to go to the new site.

ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero

2019-02-12
Yuandong Tian, Jerry Ma, Qucheng Gong, Shubho Sengupta, Zhuoyuan Chen, James Pinkerton, C. Lawrence Zitnick

Abstract

The AlphaGo, AlphaGo Zero, and AlphaZero series of algorithms are a remarkable demonstration of deep reinforcement learning’s capabilities, achieving superhuman performance in the complex game of Go with progressively increasing autonomy. However, many obstacles remain in the understanding of and usability of these promising approaches by the research community. Toward elucidating unresolved mysteries and facilitating future research, we propose ELF OpenGo, an open-source reimplementation of the AlphaZero algorithm. ELF OpenGo is the first open-source Go AI to convincingly demonstrate superhuman performance with a perfect (20:0) record against global top professionals. We apply ELF OpenGo to conduct extensive ablation studies, and to identify and analyze numerous interesting phenomena in both the model training and in the gameplay inference procedures. Our code, models, selfplay datasets, and auxiliary data are publicly available.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1902.04522

PDF

http://arxiv.org/pdf/1902.04522


Similar Posts

Comments