DeepNash
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
- 1 December 2022
- Authors
- Julien Perolat, Bart de Vylder, Daniel Hennes, Eugene Tarassov, Florian Strub, Vincent de Boer, Paul Muller, Jerome T. Connor, Neil Burch, Thomas Anthony, Stephen McAleer, Romuald Elie, Sarah H. Cen, Zhe Wang, Audrunas Gruslys, Aleksandra Malysheva, Mina Khan, Sherjil Ozair, Finbarr Timbers, Toby Pohlen, Tom Eccles, Mark Rowland, Marc Lanctot, Jean-Baptiste Lespiau, Bilal Piot, Shayegan Omidshafie…
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Games
- Task
- Stratego
- Approach
- Reinforcement learning
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
- 2,109,703,680,000 tokens
768 * 7.21M trajectories? (Table S1) 768 * 7.21M = 5,537,280,000 https://www.science.org/doi/suppl/10.1126/science.add4679/suppl_file/science.add4679_sm.pdf
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
the training code used to be here but not anymore https://github.com/google-deepmind/open_spiel/tree/master/open_spiel/python/algorithms/rnad
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
- 245
DeepNash beat existing state-of-the-art AI methods in Stratego and achieved a year-to-date (2022) and all-time top-three ranking on the Gravon games platform, competing with human expert players.
Sources
Where this record came from and when it was last checked.
- Reference
- Mastering the game of Stratego with model-free multiagent reinforcement learning
- Last updated
- 1 January 2026
What the numbers mean
Background
DeepNash was published by DeepMind, in United Kingdom of Great Britain and Northern Ireland, in December 2022. It comes out of industry.
It works in Games, and is recorded as doing stratego.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
How it was trained
It was trained on about 2,109,703,680,000 tokens of text.
The reason it appears in this catalogue at all is sOTA improvement.
Answers
DeepNash — common questions
What is DeepNash used for?
DeepNash works in Games, and is recorded as handling stratego. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run DeepNash?
None. DeepNash 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 DeepNash open source?
No. DeepNash has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does DeepNash have?
No parameter count has been published for DeepNash, which is why no memory or speed figure appears on this page.
Who created DeepNash?
DeepNash was published by DeepMind, based in United Kingdom of Great Britain and Northern Ireland, categorised as industry.
When was DeepNash released?
DeepNash was published in December 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
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.