AI models
Hanabi 4 player
Training compute
4.3×10¹⁸ FLOP
Parameters
764K
Published
Feb 1, 2019
Hanabi 4 player is an AI model developed by DeepMind, University of Oxford, Carnegie Mellon University (CMU) and Google Brain (United Kingdom and United States), first published in February 2019. It works in the games domain, on tasks such as hanabi.
Training it took an estimated 4.3×10¹⁸ FLOP of compute (estimation method: hardware). The model has 764,000 parameters. It was trained on roughly 20B datapoints. Training ran on NVIDIA V100.
Access: Unreleased. Its weights are not openly released. The reference paper has 229 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- DeepMind, University of Oxford, Carnegie Mellon University (CMU), Google Brain
- Country of organization
- United Kingdom, United States
- Domain
- Games
- Task
- Hanabi
- Training compute
- 4.3×10¹⁸ FLOP
- Compute estimation method
- Hardware
- Parameters
- 764,000
- Dataset size
- 20B
- Training hardware
- NVIDIA V100
- Model accessibility
- Unreleased
- Open weights
- No
- Citations
- 229
- Epoch confidence
- Confident
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models