DQN

Training compute

2.8×10¹⁵ FLOP

Parameters

836.1K

Published

Dec 19, 2013

DQN is an AI model developed by DeepMind (United Kingdom), first published in December 2013. It works in the games domain, on tasks such as atari.

Training it took an estimated 2.8×10¹⁵ FLOP of compute (estimation method: operation counting). The model has 836,096 parameters. It was trained on roughly 160M datapoints.

The reference paper has 13,665 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: DeepMind
Country of organization: United Kingdom
Domain: Games
Task: Atari
Training compute: 2.8×10¹⁵ FLOP
Compute estimation method: Operation counting
Parameters: 836,096
Dataset size: 160M
Citations: 13,665
Epoch confidence: Confident