Adaptive Agent

Training compute

2.8×10²¹ FLOP

Parameters

533M

Published

Jan 18, 2023

Adaptive Agent is an AI model developed by DeepMind (United Kingdom), first published in January 2023. It works in the games domain, on tasks such as open ended play.

Training it took an estimated 2.8×10²¹ FLOP of compute (estimation method: hardware). The model has 533,000,000 parameters. Training ran on Google TPU v3 for about 840 hours.

Access: Unreleased. Its weights are not openly released. The reference paper has 157 citations. Epoch AI rates the confidence of this record as speculative.

Full record

Organization: DeepMind
Country of organization: United Kingdom
Domain: Games
Task: Open ended play
Training compute: 2.8×10²¹ FLOP
Compute estimation method: Hardware
Parameters: 533,000,000
Training hardware: Google TPU v3
Training time: 840 h
Model accessibility: Unreleased
Open weights: No
Citations: 157
Epoch confidence: Speculative