FastTD3/fast_td3
Younggyo Seo 6e890eebd2
Support FastTD3 + SimbaV2 (#13)
- 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
2025-06-15 12:49:59 -07:00
..
environments black formatting and update tuned_reward for T1 2025-05-29 08:29:44 +00:00
__init__.py Initial Public Release 2025-05-29 01:49:23 +00:00
fast_td3_deploy.py Support FastTD3 + SimbaV2 (#13) 2025-06-15 12:49:59 -07:00
fast_td3_simbav2.py Support FastTD3 + SimbaV2 (#13) 2025-06-15 12:49:59 -07:00
fast_td3_utils.py Support FastTD3 + SimbaV2 (#13) 2025-06-15 12:49:59 -07:00
fast_td3.py Fix replay buffer issues when n_steps > 1 (#7) 2025-06-07 01:20:48 -04:00
hyperparams.py Support FastTD3 + SimbaV2 (#13) 2025-06-15 12:49:59 -07:00
train.py Support FastTD3 + SimbaV2 (#13) 2025-06-15 12:49:59 -07:00
training_notebook.ipynb memory optimization for playground 2025-05-29 06:58:28 +00:00