pick-place-v2-sf / README.md
qgallouedec's picture
qgallouedec HF staff
Upload . with huggingface_hub
a82259d
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: pick-place-v2
type: pick-place-v2
metrics:
- type: mean_reward
value: 33.42 +/- 41.15
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **pick-place-v2** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r qgallouedec/pick-place-v2-sf
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m enjoy --algo=APPO --env=pick-place-v2 --train_dir=./train_dir --experiment=pick-place-v2-sf
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m train --algo=APPO --env=pick-place-v2 --train_dir=./train_dir --experiment=pick-place-v2-sf --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.