mlsanityData to 14 Oct 2026

ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero

arXiv 1902.04522 ↗First posted 12 Feb 2019cs.AI cs.LG stat.MLcited by 39

Not on the map. Why?

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/.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 10; 2022: 12; 2023: 5; 2024: 3; 2025: 3; 2026: 6.

39 papers.

Sort:

By area:

  1. 2021Mastering Atari Games with Limited Datacited by 237
  2. 2021Scaling Scaling Laws with Board Gamescited by 63
  3. 2021Rethinking "Batch" in BatchNormcited by 45
  4. 2025LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Trainingcited by 42
  5. 2022Adversarial Policies Beat Superhuman Go AIscited by 29
  6. 2023Replicability in Reinforcement Learningcited by 21
  7. 2021Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Gamescited by 18
  8. 2022Are AlphaZero-like Agents Robust to Adversarial Perturbations?cited by 14
  9. 2023MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Gamescited by 14
  10. 2022Evaluation Beyond Task Performance: Analyzing Concepts in AlphaZero in Hexcited by 8
  11. 2021A Novel Approach to Solving Goal-Achieving Problems for Board Gamescited by 7
  12. 2021Transfer of Fully Convolutional Policy-Value Networks Between Games and Game Variantscited by 6
27 more
  1. 2022Reinforcement Learning in Practice: Opportunities and Challengescited by 6
  2. 2021Batch Monte Carlo Tree Searchcited by 5
  3. 2021Deep Synoptic Monte Carlo Planning in Reconnaissance Blind Chesscited by 4
  4. 2023Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learningcited by 4
  5. 2021Improving Model and Search for Computer Gocited by 3
  6. 2022Spatial State-Action Features for General Gamescited by 3
  7. 2022Understanding Game-Playing Agents with Natural Language Annotationscited by 3
  8. 2022Impartial Games: A Challenge for Reinforcement Learningcited by 3
  9. 2022Brick Tic-Tac-Toe: Exploring the Generalizability of AlphaZero to Novel Test Environmentscited by 2
  10. 2024Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Mapscited by 2
  11. 2022PGD: A Large-scale Professional Go Dataset for Data-driven Analyticscited by 1
  12. 2022Mastering Spatial Graph Prediction of Road Networkscited by 1
  13. 2023Diversity is Strength: Mastering Football Full Game with Interactive Reinforcement Learning of Multiple AIscited by 1
  14. 2025Strength Estimation and Human-Like Strength Adjustment in Gamescited by 1
  15. 2026Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Gamescited by 1
  16. 2021OLIVAW: Mastering Othello without Human Knowledge, nor a Fortunecited by 0
  17. 2022The cost of passing -- using deep learning AIs to expand our understanding of the ancient game of Gocited by 0
  18. 2022The ProfessionAl Go annotation datasEt (PAGE)cited by 0
  19. 2023CH-Go: Online Go System Based on Chunk Data Storagecited by 0
  20. 2024Enhancing Reinforcement Learning Through Guided Searchcited by 0
  21. 2024Bridging Local and Global Knowledge via Transformer in Board Gamescited by 0
  22. 2025A Study of Solving Life-and-Death Problems in Go Using Relevance-Zone Based Solverscited by 0
  23. 2026Mastering the Game of Go with Self-play Experience Replaycited by 0
  24. 2026Fast and Robust Convergence Rate for TD(0) with Linear Function Approximation, Universal Learning Steps and I.I.D. Samplescited by 0
  25. 2026Continual-RL for Generalization in Autonomous Racing on the RoboRacer Platformcited by 0
  26. 2026Belief-Guided Decision Making with Uncertainty Gating in the Game of Gocited by 0
  27. 2026TreeFlex: Agents Navigating Their Own Search Treescited by 0