c354ead107
- Modified codes to be compatible with torch.compile - Modified empirical normalizer to use in-place operator to avoid costly __setattr__ - Parallel soft Q-update - As a default option, we disabled gradient norm clipping as it is quite expensive |
||
|---|---|---|
| .. | ||
| 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 | ||