6e890eebd2
- Support hyperspherical normalization - Support loading FastTD3 + SimbaV2 for both training and inference - Support (experimental) reward normalization that uses SimbaV2's formulation -- not working that well though - Updated README for FastTD3 + SimbaV2 |
||
|---|---|---|
| .. | ||
| environments | ||
| __init__.py | ||
| fast_td3_deploy.py | ||
| fast_td3_simbav2.py | ||
| fast_td3_utils.py | ||
| fast_td3.py | ||
| hyperparams.py | ||
| train.py | ||
| training_notebook.ipynb | ||