Hide and Seek

Training compute

1.1×10¹⁸ FLOP

Parameters

1.6M

Published

Sep 17, 2019

Hide and Seek is an AI model developed by OpenAI (United States), first published in September 2019. It works in the games domain, on tasks such as hide and seek.

Training it took an estimated 1.1×10¹⁸ FLOP of compute (estimation method: operation counting,third-party estimation). The model has 1,600,000 parameters. It was trained on roughly 120B datapoints.

Access: Unreleased. Its weights are not openly released. The reference paper has 752 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: OpenAI
Country of organization: United States
Domain: Games
Task: Hide and seek
Training compute: 1.1×10¹⁸ FLOP
Compute estimation method: Operation counting, Third-party estimation
Parameters: 1,600,000
Dataset size: 120B
Model accessibility: Unreleased
Open weights: No
Citations: 752
Epoch confidence: Confident