DD-PPO
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
- Georgia Institute of Technology,Facebook AI Research,Oregon State University,Simon Fraser University
- Organisation type
- Academia,Industry,Academia,Academia
- Country
- United States of America, France, Canada
- Published
- 19 December 2019
- Authors
- Erik Wijmans, Abhishek Kadian, Ari Morcos, Stefan Lee, Irfan Essa, Devi Parikh, Manolis Savva, Dhruv Batra
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Robotics
- Task
- Object detection
- Approach
- Reinforcement learning
- Numerical format
- FP32
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
- 2,500,000,000 tokens
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
- 7.8 × 10²⁰ FLOP
- How it was established
- Hardware
"Using DD-PPO, we train agents for 2.5 Billion steps of experience with 64 Tesla V100 GPUs in 2.75 days – 180 GPU-days of training" 125 teraFLOP/s (exact V100 model not specified) * 180 * 24 * 3600 * 0.4 (assumed utilization) = 7.8e20
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- NVIDIA V100
- Chips used
- 64
- Wall-clock time
- 66 hours
- Power draw
- 39.3 kW
- Compute cost
- $1,927
2.75 days
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
- Training code
- Unreleased
MIT license for environment used to train. doesn't seem like it has training code for this model. https://github.com/facebookresearch/habitat-lab
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
- Record confidence
- Likely
- Citations
- 611
"This agent achieves state-of-art on the Habitat Challenge 2019 RGB track (rank 2 entry has 0.89 SPL)."
Sources
Where this record came from and when it was last checked.
- Reference
- DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
DD-PPO was published by Georgia Institute of Technology,Facebook AI Research,Oregon State University,Simon Fraser University, in United States of America, in December 2019. It comes out of academia,Industry,Academia,Academia.
It works in Robotics, and is recorded as doing object detection.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
How it was trained
Training it took roughly 7.8 × 10²⁰ FLOP of computation, on NVIDIA V100 — a measure of what producing the model cost, not of how fast it answers.
The training set ran to roughly 2,500,000,000 tokens.
The reason it appears in this catalogue at all is sOTA improvement.
Answers
DD-PPO — common questions
How much compute was used to train DD-PPO?
Around 7.8 × 10²⁰ FLOP, on NVIDIA V100. 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.
What GPU do I need to run DD-PPO?
None. DD-PPO 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 DD-PPO open source?
No. DD-PPO has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does DD-PPO have?
No parameter count has been published for DD-PPO, which is why no memory or speed figure appears on this page.
Who created DD-PPO?
DD-PPO was published by Georgia Institute of Technology,Facebook AI Research,Oregon State University,Simon Fraser University, based in United States of America, categorised as academia,Industry,Academia,Academia.
When was DD-PPO released?
DD-PPO was published in December 2019. 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 DD-PPO used for?
DD-PPO works in Robotics, and is recorded as handling object detection. These are the areas it was designed around; they describe intent rather than a hard boundary.
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.