TD-Gammon

Closed weights IBM 25K parameters May 1992

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
IBM
Organisation type
Industry
Country
United States of America
Published
1 May 1992
Authors
G Tesauro

What it does

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

Domain
Games
Task
Backgammon

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
25K

"The best performance was obtained with a network containing 80 hidden units and over 25,000 weights."

Training data
6,300,000 tokens

"This network was trained for over 300,000 training games" Each backgammon game has an avg of around 21 movements https://www.bkgm.com/rgb/rgb.cgi?view+712

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
1.8 × 10¹³ FLOP

Extracted from AI and Compute (https://openai.com/blog/ai-and-compute/) charts by using https://automeris.io/WebPlotDigitizer/. OpenAI estimate: 1.8e13 Hardware estimate (likely overestimates due to simulation effort) "on an IBM RS/6000 workstation, the smallest network was trained in several hours, while the largest net required two weeks of simulation time." IBM RS/6000 achieves 1.5 GFLOPS on Linpack (https://link.springer.com/rwe/10.1007/978-0-387-09766-4_232) 14*24*60*60*0.5*1500000000=9.…

How it was established
Third-party estimation,Operation counting,Hardware

How it is classified

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

Frontier model
Yes
Why it is tracked
Highly cited,Historical significance
Record confidence
Speculative
Citations
1,344

Sources

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

Reference
Practical Issues in Temporal Difference Learning
Last updated
28 November 2025

What the numbers mean

Background

TD-Gammon was published by IBM, in United States of America, in May 1992. industry is the category the publisher falls under.

It works in Games, and is recorded as doing backgammon.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

Training and provenance

Producing it required around 1.8 × 10¹³ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

Around 6,300,000 tokens went into training it.

The reason it appears in this catalogue at all is highly cited,Historical significance.

Answers

TD-Gammon — common questions

01

What is TD-Gammon used for?

TD-Gammon works in Games, and is recorded as handling backgammon. 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.

02

How much compute was used to train TD-Gammon?

Around 1.8 × 10¹³ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

03

What GPU do I need to run TD-Gammon?

None. TD-Gammon 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.

04

Is TD-Gammon open source?

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

05

How many parameters does TD-Gammon have?

TD-Gammon has 25K parameters. "The best performance was obtained with a network containing 80 hidden units and over 25,000 weights.". 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.

06

Who created TD-Gammon?

TD-Gammon was published by IBM, based in United States of America, categorised as industry.

07

When was TD-Gammon released?

TD-Gammon was published in May 1992. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

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.