Go-explore
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
- Uber AI,OpenAI
- Organisation type
- Industry,Industry
- Country
- United States of America
- Published
- 27 April 2020
- Authors
- Adrien Ecoffet, Joost Huizinga, Joel Lehman, Kenneth O. Stanley, Jeff Clune
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
- 40,000,000,000 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
- Open (non-commercial)
non-commercial code: https://github.com/uber-research/go-explore/blob/master/LICENSE
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
- 436
not an absolute SOTA "GoExplore solves all heretofore unsolved Atari games (meaning those for which algorithms could not previously outperform humans when evaluated following current community standards for Atari3) and surpasses the state of the art on all hard-exploration games" "the final mean performance of Go-Explore is both superhuman and surpasses the state of the art in all eleven games (except in Freeway where both Go-Explore and the state of the art reach the maximum score; Fig. 2b). …
Sources
Where this record came from and when it was last checked.
- Reference
- First return, then explore
- Last updated
- 25 May 2026
What the numbers mean
Background
Go-explore was published by Uber AI,OpenAI, in United States of America, in April 2020. The organisation is categorised as industry,Industry.
It works in Games, and is recorded as doing atari.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
How it was trained
Around 40,000,000,000 tokens went into training it.
It is tracked in the underlying dataset for one reason in particular: sOTA improvement.
Answers
Go-explore — common questions
Who created Go-explore?
Go-explore was published by Uber AI,OpenAI, based in United States of America, categorised as industry,Industry.
When was Go-explore released?
Go-explore was published in April 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 Go-explore used for?
Go-explore works in Games, and is recorded as handling atari. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run Go-explore?
None. Go-explore 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 Go-explore open source?
No. Go-explore has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does Go-explore have?
No parameter count has been published for Go-explore, which is why no memory or speed figure appears on this page.
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.