HyperNEAT
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
- University of Texas at Austin
- Organisation type
- Academia
- Country
- United States of America
- Published
- 5 March 2014
- Authors
- M Hausknecht, J Lehman
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
- 239.7K
- Training data
- 750,000,000 tokens
"The ANN consists of three layers (Fig. 3): a substrate layer inwhich information from the game screen (raw pixels, objects, ornoise) is given as input to the network; a processing layer whichadds a nonlinear internal representation; and a nonlinear outputlayer from which actions are read and conveyed to the Atari em-ulator. Both the input and output layers are fully connected tothe processing layer. The substrate dimensionality of the inputand processinglayers is 810 in the case of the object r…
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
- Citations
- 195
"Neuroevolution ameliorates these problems and evolved policies achieve state-of-the-art results, even surpassing human high scores on three games"
Sources
Where this record came from and when it was last checked.
- Reference
- A Neuroevolution Approach to General Atari Game Playing
- Last updated
- 28 November 2025
What the numbers mean
About this model
HyperNEAT was published by University of Texas at Austin, in United States of America, in March 2014. It comes out of academia.
It works in Games, and is recorded as doing atari.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
What went into building it
The training set ran to roughly 750,000,000 tokens.
It is tracked in the underlying dataset for one reason in particular: sOTA improvement.
Answers
HyperNEAT — common questions
Is HyperNEAT open source?
The licensing for HyperNEAT was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does HyperNEAT have?
HyperNEAT has 239.7K parameters. "The ANN consists of three layers (Fig. 3): a substrate layer inwhich information from the game screen (raw pixels, objects, ornoise) is given as input to the network; a processing layer whichadds a nonlinear internal representation; and a nonlinear outputlayer from which actions are read and conveyed to the Atari em-ulator. Both the input and output layers are fully connected tothe processing layer. The substrate dimensionality of the inputand processinglayers is 810 in the case of the object repre-sentation and 1621 for the pixel and noise representations.3The output layer consists of a 33 substrate mirroring the ninepossible directions of the Atari 2600 joystick and a single noderepresenting thefire button". 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.
Who created HyperNEAT?
HyperNEAT was published by University of Texas at Austin, based in United States of America, categorised as academia.
When was HyperNEAT released?
HyperNEAT was published in March 2014. 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 HyperNEAT used for?
HyperNEAT works in Games, and is recorded as handling atari. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
What GPU do I need to run HyperNEAT?
None. HyperNEAT 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.
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.