PDF] ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero

ELF OpenGo is the first open-source Go AI to convincingly demonstrate superhuman performance with a perfect (20:0) record against global top professionals and is proposed, anopen-source reimplementation of the AlphaZero algorithm. 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.

PDF] Accelerating and Improving AlphaZero Using Population Based Training

PDF] Improving Model and Search for Computer Go

Multiplayer AlphaZero – arXiv Vanity

Evolutionary Reinforcement Learning: A Survey

Accelerating Self-Play Learning in Go – arXiv Vanity

LightZero/README.zh.md at main · opendilab/LightZero · GitHub

PDF] From Gameplay to Symbolic Reasoning: Learning SAT Solver Heuristics in the Style of Alpha(Go) Zero

Electronics, Free Full-Text

Facebook Open-Sources Improved Go Bot and Huge Game Library, by Synced, SyncedReview

Electronics, Free Full-Text