DQN

Closed weights DeepMind 836.1K parameters December 2013

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
DeepMind
Organisation type
Industry
Country
United Kingdom of Great Britain and Northern Ireland
Published
19 December 2013
Authors
V Mnih, K Kavukcuoglu, D Silver, A Graves

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Games
Task
Atari

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
836.1K

"The input to the neural network consists is an 84 × 84 × 4 image produced by φ. The first hidden layer convolves 16 8 × 8 filters with stride 4 with the input image and applies a rectifier nonlinearity [10, 18]. The second hidden layer convolves 32 4 × 4 filters with stride 2, again followed by a rectifier nonlinearity. The final hidden layer is fully-connected and consists of 256 rectifier units. The output layer is a fully connected linear layer with a single output for each valid action. The…

Training data
160,000,000 tokens

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
2.8 × 10¹⁵ FLOP

Network is 84x84x4 input, 16, 8x8, stride 4, 32 4x4 stride 2, 256 fully connected First layer: 20*20*4*16*8*8 = 1638400 Second layer: 9*9*16*32*4*4 = 663552 Third layer: 9*9*32*256 = 663552 Total ~ 2965504 2965504 * 5M updates * 32 batch size * 2 multiply-add * 3 backward pass = 2965504*50000*100*32*6 = 2846883840000000

How it was established
Operation counting

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked
Highly cited,SOTA improvement

"Our approach gave state-of-the-art results in six of the seven games it was tested on, with no adjustment of the architecture or hyperparameters."

Record confidence
Confident
Citations
13,665

Sources

Where this record came from and when it was last checked.

Reference
Playing Atari with Deep Reinforcement Learning
Last updated
25 May 2026

What the numbers mean

Where it came from

DQN was published by DeepMind, in the country recorded as United Kingdom of Great Britain and Northern Ireland, during December 2013. It comes out of an organisation categorised as industry.

It works in the domain of Games, and is recorded as performing the task of atari.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

Training and provenance

Producing it required arithmetic totalling around 2.8 × 10¹⁵ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

It was trained on a corpus of about 160,000,000 tokens of text.

It is tracked in the underlying dataset for one reason in particular: highly cited,SOTA improvement.

Answers

DQN — common questions

01

DQN— is it open source?

The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

02

DQN— how many parameters does it have?

It has a parameter count of 836.1K. "The input to the neural network consists is an 84 × 84 × 4 image produced by φ. The first hidden layer convolves 16 8 × 8 filters with stride 4 with the input image and applies a rectifier nonlinearity [10, 18]. The second hidden layer convolves 32 4 × 4 filters with stride 2, again followed by a rectifier nonlinearity. The final hidden layer is fully-connected and consists of 256 rectifier units. The output layer is a fully connected linear layer with a single output for each valid action. The number of valid actions varied between 4 and 18 on the games we considered." Parameter: 4*16*8*8+16*32*4*4+10*10*32*256+18*256=836096. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

03

DQN— who created it?

It was published by DeepMind, based in United Kingdom of Great Britain and Northern Ireland, an organisation categorised as industry.

04

DQN— when was it released?

It was published in December 2013. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

DQN— what is it used for?

It works in the domain of Games, and is recorded as handling the task of atari. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

06

DQN— how much compute was used to train it?

Training consumed around 2.8 × 10¹⁵ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

07

DQN— what GPU do I need to run it?

None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

Source

Original publication

Record last updated 25 May 2026

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.