Agent57
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
- 30 March 2020
- Authors
- AP Badia, B Piot, S Kapturowski
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
- tokens
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- Unreleased
- Training code
- Unreleased
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
- Record confidence
- Unknown
- Citations
- 587
"We propose Agent57, the first deep RL agent that outperforms the standard human benchmark on all 57 Atari games"
Sources
Where this record came from and when it was last checked.
- Reference
- Agent57: Outperforming the Atari Human Benchmark
- Last updated
- 25 May 2026
What the numbers mean
Background
Agent57 was published by DeepMind, in United Kingdom of Great Britain and Northern Ireland, in March 2020. industry is the category the publisher falls under.
It works in Games, and is recorded as doing atari.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
What went into building it
The reason it appears in this catalogue at all is sOTA improvement.
Answers
Agent57 — common questions
What GPU do I need to run Agent57?
None. Agent57 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.
Is Agent57 open source?
No. Agent57 has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does Agent57 have?
No parameter count has been published for Agent57, which is why no memory or speed figure appears on this page.
Who created Agent57?
Agent57 was published by DeepMind, based in United Kingdom of Great Britain and Northern Ireland, categorised as industry.
When was Agent57 released?
Agent57 was published in March 2020. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is Agent57 used for?
Agent57 works in Games, and is recorded as handling 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.
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.