DQN-2015

Closed weights Google 1.7M parameters February 2015

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
Google
Organisation type
Industry
Country
United States of America
Published
25 February 2015
Authors
Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, Demis Hassabis

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
1.7M

"The input to the neural network consists of an 84x84x4 image produced by the preprocess-ing mapw. The first hidden layer convolves 32 filters of 8x8 with stride 4 with theinput image and applies a rectifier nonlinearity. The second hidden layer con-volves 64 filters of 4x4 with stride 2, again followed by a rectifier nonlinearity.This is followedby a thirdconvolutional layer thatconvolves 64 filtersof 3x3 withstride 1 followed by a rectifier. The final hidden layer is fully-connected and con-si…

Training data
12,500,000 tokens

Methods: "we trained for a total of 50 million frames"

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
Citations
25,403

Sources

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

Reference
Human-level control through deep reinforcement learning
Last updated
28 November 2025

What the numbers mean

Where it came from

DQN-2015 was published by Google, in the country recorded as United States of America, during February 2015. The category the publisher falls under is industry.

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

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

Training and provenance

Training consumed a corpus of around 12,500,000 tokens of text.

Its inclusion criterion: highly cited.

Answers

DQN-2015 — common questions

01

DQN-2015— 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.

02

DQN-2015— 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.

03

DQN-2015— how many parameters does it have?

It has a parameter count of 1.7M. "The input to the neural network consists of an 84x84x4 image produced by the preprocess-ing mapw. The first hidden layer convolves 32 filters of 8x8 with stride 4 with theinput image and applies a rectifier nonlinearity. The second hidden layer con-volves 64 filters of 4x4 with stride 2, again followed by a rectifier nonlinearity.This is followedby a thirdconvolutional layer thatconvolves 64 filtersof 3x3 withstride 1 followed by a rectifier. The final hidden layer is fully-connected and con-sists of 512 rectifier units. The output layer is a fully-connected linear layer with asingle output for each valid action. The number of valid actions varied between 4 and 18 on the games we considered." Example num params here: https://colab.research.google.com/drive/1Ty6SFYWd7EcKoxJohucL2OdiLR_3oXnI?usp=sharing. 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.

04

DQN-2015— who created it?

It was published by Google, based in United States of America, an organisation categorised as industry.

05

DQN-2015— when was it released?

It was published in February 2015. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

DQN-2015— what is it used for?

It works in the domain of Games, and is recorded as handling the task of atari. These are the areas it was designed around; they describe intent rather than a hard boundary.

Source

Original publication

Record last updated 28 November 2025

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.