Q-learning
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 London
- Organisation type
- Academia
- Country
- United Kingdom of Great Britain and Northern Ireland
- Published
- 1 January 1989
- Authors
- Christopher Watkins
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Robotics, Games
- Task
- Route finding, System control
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
- 200,000 tokens
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
- Highly cited
- Record confidence
- Unknown
- Citations
- 8,025
Sources
Where this record came from and when it was last checked.
- Reference
- Learning from delayed rewards
- Last updated
- 28 November 2025
What the numbers mean
About this model
Q-learning was published by University of London, in United Kingdom of Great Britain and Northern Ireland, in January 1989. academia is the category the publisher falls under.
It works in Robotics, Games, and is recorded as doing route finding, System control.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Training and provenance
Around 200,000 tokens went into training it.
The reason it appears in this catalogue at all is highly cited.
Answers
Q-learning — common questions
Is Q-learning open source?
The licensing for Q-learning 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 Q-learning have?
No parameter count has been published for Q-learning, which is why no memory or speed figure appears on this page.
Who created Q-learning?
Q-learning was published by University of London, based in United Kingdom of Great Britain and Northern Ireland, categorised as academia.
When was Q-learning released?
Q-learning was published in January 1989. 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 Q-learning used for?
Q-learning works in Robotics, Games, and is recorded as handling route finding, System control. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run Q-learning?
None. Q-learning 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.