Intelligent Go-Explore (IGE)
No estimate
No hardware requirements for this model
This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.
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
- University of British Columbia (UBC),Vector Institute,CIFAR AI Research
- Organisation type
- Academia,Academia,Research collective
- Country
- Canada
- Published
- 3 December 2024
- Authors
- Cong Lu, Shengran Hu, Jeff Clune
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Games
- Task
- Game of 24 (24 puzzle)
- Base model
- GPT-4 Turbo (Nov 2023)
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
- Open — downloadable
- Model access
- Open weights (unrestricted)
- Training code
- Unreleased
MIT license https://github.com/conglu1997/intelligent-go-explore seems to be just inference code, not training code
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Unknown
Sources
Where this record came from and when it was last checked.
- Reference
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models
- Last updated
- 11 February 2026
What the numbers mean
About this model
Intelligent Go-Explore (IGE) was published by University of British Columbia (UBC),Vector Institute,CIFAR AI Research, in Canada, in December 2024. It comes out of academia,Academia,Research collective.
It works in Games, and is recorded as doing game of 24 (24 puzzle).
Its starting point was GPT-4 Turbo (Nov 2023) — most models at this scale are adapted from an existing base rather than built from nothing.
Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.
Answers
Intelligent Go-Explore (IGE) — common questions
Is Intelligent Go-Explore (IGE) open source?
Its weights are published, so Intelligent Go-Explore (IGE) can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.
How many parameters does Intelligent Go-Explore (IGE) have?
No parameter count has been published for Intelligent Go-Explore (IGE), which is why no memory or speed figure appears on this page.
Who created Intelligent Go-Explore (IGE)?
Intelligent Go-Explore (IGE) was published by University of British Columbia (UBC),Vector Institute,CIFAR AI Research, based in Canada, categorised as academia,Academia,Research collective.
When was Intelligent Go-Explore (IGE) released?
Intelligent Go-Explore (IGE) was published in December 2024. 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 Intelligent Go-Explore (IGE) used for?
Intelligent Go-Explore (IGE) works in Games, and is recorded as handling game of 24 (24 puzzle). These are the areas it was designed around; they describe intent rather than a hard boundary.
Where can I download Intelligent Go-Explore (IGE)?
The weights for Intelligent Go-Explore (IGE) are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
What GPU do I need to run Intelligent Go-Explore (IGE)?
We cannot say. Intelligent Go-Explore (IGE) has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.
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.