MetaMimic

Closed weights Google 22M parameters October 2018

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
Google
Organisation type
Industry
Country
United States of America
Published
11 October 2018
Authors
Tom Le Paine, Sergio Gomez

What it does

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

Domain
Robotics
Task
Robotic manipulation
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.

Parameters
22M

"This representational demand motivates the introduction of high-capacity deep neural networks. We found the architecture, shown in Figure 3, with residual connections, 20 convolution layers with 512 channels for a total of 22 million parameters, and instance normalization to drastically improve performance, as shown in Figure 6 of the Experiments section."

Training data
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
SOTA improvement

"By retaining and taking advantage of all its experiences, MetaMimic also substantially outperforms the state-of-the-art D4PG RL agent, when D4PG uses only the current task experiences." I haven't found any standard benchmarks or metrics that they claim SOTA on

Citations
26

Sources

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

Reference
One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL
Last updated
28 November 2025

What the numbers mean

Background

MetaMimic was published by Google, in United States of America, in October 2018. The organisation is categorised as industry.

It works in Robotics, and is recorded as doing robotic manipulation.

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

What went into building it

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Answers

MetaMimic — common questions

01

What is MetaMimic used for?

MetaMimic works in Robotics, and is recorded as handling robotic manipulation. These are the areas it was designed around; they describe intent rather than a hard boundary.

02

What GPU do I need to run MetaMimic?

None. MetaMimic 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 MetaMimic open source?

The licensing for MetaMimic 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 MetaMimic have?

MetaMimic has 22M parameters. "This representational demand motivates the introduction of high-capacity deep neural networks. We found the architecture, shown in Figure 3, with residual connections, 20 convolution layers with 512 channels for a total of 22 million parameters, and instance normalization to drastically improve performance, as shown in Figure 6 of the Experiments section.". 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 MetaMimic?

MetaMimic was published by Google, based in United States of America, categorised as industry.

06

When was MetaMimic released?

MetaMimic was published in October 2018. 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.