Advantage Learning

Closed weights Google DeepMind December 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 DeepMind
Organisation type
Industry
Country
United States of America
Published
15 December 2015
Authors
MG Bellemare, G Ostrovski, A Guez

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.

Training data
100,000,000 tokens

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
SOTA improvement

"We use our operators to obtain state-of-the-art empirical results on the Arcade Learning Environment (Bellemare et al. 2013)."

Record confidence
Unknown
Citations
166

Sources

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

Reference
Increasing the Action Gap: New Operators for Reinforcement Learning
Last updated
25 May 2026

What the numbers mean

About this model

Advantage Learning was published by Google DeepMind, in the country recorded as United States of America, during December 2015. 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.

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

Training and provenance

The training set ran to roughly 100,000,000 tokens of text.

The reason it appears in this catalogue at all: sOTA improvement.

Answers

Advantage Learning — common questions

01

Advantage Learning— how many parameters does it have?

No parameter count has been published for it, which is why no memory or speed figure appears on this page.

02

Advantage Learning— who created it?

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

03

Advantage Learning— when was it released?

It was published in December 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.

04

Advantage Learning— what is it used for?

It works in the domain of Games, and is recorded as handling the task of atari. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

05

Advantage Learning— 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.

06

Advantage Learning— 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.

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.