Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
AsteroidsNoFrameskip-v4
Eval Results (legacy)
Instructions to use edbeeching/atari_2B_atari_asteroid_3333 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sample-factory
How to use edbeeching/atari_2B_atari_asteroid_3333 with sample-factory:
python -m sample_factory.huggingface.load_from_hub -r edbeeching/atari_2B_atari_asteroid_3333 -d ./train_dir
- Notebooks
- Google Colab
- Kaggle
Download agent.pt from edbeeching/atari_2B_atari_asteroid_3333: direct link, hf CLI and curl.
- Browser
- Download file 7 MB
-
https://huggingface.co/edbeeching/atari_2B_atari_asteroid_3333/resolve/main/agent.pt
- Command line
-
hf download hf://edbeeching/atari_2B_atari_asteroid_3333/agent.pt
-
curl -L -o agent.pt https://huggingface.co/edbeeching/atari_2B_atari_asteroid_3333/resolve/main/agent.pt
7 MB
- Xet hash:
- 1554a1e42b5eeffdaa4d6f3d972382610a2c35a74a9135d88dbb9740d3e44aaa
- Size of remote file:
- 7 MB
- SHA256:
- d72971e65fb044b2417c1fa0a39523c3b00c3a3ca7133b4ac16f1b0729a06a56
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.