Bayesian Starcraft

Closed weights Collège de France 13.1K parameters August 2011

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
Collège de France
Organisation type
Academia
Country
France
Published
31 August 2011
Authors
Gabriel Synnaeve, Pierre Bessière

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Games
Task
StarCraft

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
13.1K

It's a bayes net, parameters are probabilty tables for probability that X happens in direction i given that we go in direction i. There are 25 directions.

Training data
tokens

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Citations
86

Sources

Where this record came from and when it was last checked.

Reference
A Bayesian Model for RTS Units Control applied to StarCraft
Last updated
28 November 2025

What the numbers mean

What this model is

Bayesian Starcraft was published by Collège de France, in the country recorded as France, during August 2011. It comes out of an organisation categorised as academia.

It works in the domain of Games, and is recorded as performing the task of starCraft.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

Answers

Bayesian Starcraft — common questions

01

Bayesian Starcraft— how many parameters does it have?

It has a parameter count of 13.1K. It's a bayes net, parameters are probabilty tables for probability that X happens in direction i given that we go in direction i. There are 25 directions. 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.

02

Bayesian Starcraft— who created it?

It was published by Collège de France, based in France, an organisation categorised as academia.

03

Bayesian Starcraft— when was it released?

It was published in August 2011. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

04

Bayesian Starcraft— what is it used for?

It works in the domain of Games, and is recorded as handling the task of starCraft. 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.

05

Bayesian Starcraft— what GPU do I need to run it?

None. This 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.

06

Bayesian Starcraft— is it open source?

The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

Source

Original publication

Record last updated 28 November 2025

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.