Punish/Reward

Closed weights IEEE 0K parameters September 1973

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
IEEE
Organisation type
Industry
Country
Multinational
Published
1 September 1973
Authors
Widrow, Gupta, and Maitra

What it does

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

Domain
Games
Task
Blackjack

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
0K

Fig. 1 shows that there is a bias term, while Fig. 5 shows that the input is a sequence of 20 bits, corresponding to 20 weights. So the total number of parameters is 21.

Training data
tokens

??? Seemingly no info

How it is classified

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

Citations
397

Sources

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

Reference
Punish/Reward: Learning with a Critic in Adaptive Threshold Systems
Last updated
28 November 2025

What the numbers mean

Where it came from

Punish/Reward was published by IEEE, in Multinational, in September 1973. It comes out of industry.

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

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

Answers

Punish/Reward — common questions

01

What is Punish/Reward used for?

Punish/Reward works in Games, and is recorded as handling blackjack. These are the areas it was designed around; they describe intent rather than a hard boundary.

02

What GPU do I need to run Punish/Reward?

None. Punish/Reward 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.

03

Is Punish/Reward open source?

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

04

How many parameters does Punish/Reward have?

Punish/Reward has 0K parameters. Fig. 1 shows that there is a bias term, while Fig. 5 shows that the input is a sequence of 20 bits, corresponding to 20 weights. So the total number of parameters is 21. 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.

05

Who created Punish/Reward?

Punish/Reward was published by IEEE, based in Multinational, categorised as industry.

06

When was Punish/Reward released?

Punish/Reward was published in September 1973. 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.