# ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero

arXiv: https://arxiv.org/abs/1902.04522 · HTML: https://mlsanity.com/paper/1902.04522/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2019.

## Built on by (most cited first, 30 of 39)

- [Mastering Atari Games with Limited Data](https://mlsanity.com/paper/2111.00210/) (2021)
- [Scaling Scaling Laws with Board Games](https://mlsanity.com/paper/2104.03113/) (2021)
- [Rethinking "Batch" in BatchNorm](https://mlsanity.com/paper/2105.07576/) (2021)
- [LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training](https://mlsanity.com/paper/2505.24034/) (2025)
- [Adversarial Policies Beat Superhuman Go AIs](https://mlsanity.com/paper/2211.00241/) (2022)
- [Replicability in Reinforcement Learning](https://mlsanity.com/paper/2305.19562/) (2023)
- [Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games](https://mlsanity.com/paper/2102.08903/) (2021)
- [Are AlphaZero-like Agents Robust to Adversarial Perturbations?](https://mlsanity.com/paper/2211.03769/) (2022)
- [MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games](https://mlsanity.com/paper/2310.11305/) (2023)
- [Evaluation Beyond Task Performance: Analyzing Concepts in AlphaZero in Hex](https://mlsanity.com/paper/2211.14673/) (2022)
- [A Novel Approach to Solving Goal-Achieving Problems for Board Games](https://mlsanity.com/paper/2112.02563/) (2021)
- [Transfer of Fully Convolutional Policy-Value Networks Between Games and Game Variants](https://mlsanity.com/paper/2102.12375/) (2021)
- [Reinforcement Learning in Practice: Opportunities and Challenges](https://mlsanity.com/paper/2202.11296/) (2022)
- [Batch Monte Carlo Tree Search](https://mlsanity.com/paper/2104.04278/) (2021)
- [Deep Synoptic Monte Carlo Planning in Reconnaissance Blind Chess](https://mlsanity.com/paper/2110.01810/) (2021)
- [Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2305.04819/) (2023)
- [Improving Model and Search for Computer Go](https://mlsanity.com/paper/2102.03467/) (2021)
- [Spatial State-Action Features for General Games](https://mlsanity.com/paper/2201.06401/) (2022)
- [Understanding Game-Playing Agents with Natural Language Annotations](https://mlsanity.com/paper/2204.07531/) (2022)
- [Impartial Games: A Challenge for Reinforcement Learning](https://mlsanity.com/paper/2205.12787/) (2022)
- [Brick Tic-Tac-Toe: Exploring the Generalizability of AlphaZero to Novel Test Environments](https://mlsanity.com/paper/2207.05991/) (2022)
- [Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Maps](https://mlsanity.com/paper/2412.12024/) (2024)
- [PGD: A Large-scale Professional Go Dataset for Data-driven Analytics](https://mlsanity.com/paper/2205.00254/) (2022)
- [Mastering Spatial Graph Prediction of Road Networks](https://mlsanity.com/paper/2210.00828/) (2022)
- [Diversity is Strength: Mastering Football Full Game with Interactive Reinforcement Learning of Multiple AIs](https://mlsanity.com/paper/2306.15903/) (2023)
- [Strength Estimation and Human-Like Strength Adjustment in Games](https://mlsanity.com/paper/2502.17109/) (2025)
- [Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Games](https://mlsanity.com/paper/2602.10894/) (2026)
- [OLIVAW: Mastering Othello without Human Knowledge, nor a Fortune](https://mlsanity.com/paper/2103.17228/) (2021)
- [The cost of passing -- using deep learning AIs to expand our understanding of the ancient game of Go](https://mlsanity.com/paper/2208.12643/) (2022)
- [The ProfessionAl Go annotation datasEt (PAGE)](https://mlsanity.com/paper/2211.01559/) (2022)

## Abstract (arXiv)

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/.