ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero
This provides the research community with a usable tool for studying deep reinforcement learning in Go, though it is incremental as a reimplementation.
The authors tackled the lack of accessible and high-performing open-source implementations of AlphaZero for Go by developing ELF OpenGo, which achieved superhuman performance with a perfect 20:0 record against top professionals.
The AlphaGo, AlphaGo Zero, and AlphaZero series of algorithms are remarkable demonstrations 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 at https://ai.facebook.com/tools/elf-opengo/.