TRPO
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 California (UC) Berkeley
- Organisation type
- Academia
- Country
- United States of America
- Published
- 19 February 2015
- Authors
- John Schulman, Sergey Levine, Philipp Moritz, Michael I. Jordan, Pieter Abbeel
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Games
- Task
- Atari
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
- 33.5K
- Training data
- tokens
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Wall-clock time
- 30 hours
"The 500 iterations of our algorithm took about 30 hours (with slight variation between games) on a 16-core computer."
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- Unreleased
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
- Confident
- Citations
- 8,305
Also listed in Denis Panjuta's List of 100+ AI Algorithms
Sources
Where this record came from and when it was last checked.
- Reference
- Trust Region Policy Optimization
- Last updated
- 28 November 2025
What the numbers mean
What this model is
TRPO was published by University of California (UC) Berkeley, in United States of America, in February 2015. The organisation is categorised as academia.
It works in Games, and is recorded as doing atari.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Training and provenance
Its inclusion criterion is highly cited.
Answers
TRPO — common questions
What GPU do I need to run TRPO?
None. TRPO 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.
Is TRPO open source?
No. TRPO has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does TRPO have?
TRPO has 33.5K parameters. 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.
Who created TRPO?
TRPO was published by University of California (UC) Berkeley, based in United States of America, categorised as academia.
When was TRPO released?
TRPO was published in February 2015. 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 TRPO used for?
TRPO works in Games, and is recorded as handling atari. 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.
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.