wangzixiang
/
lerobot
mirror of https://github.com/huggingface/lerobot.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Refine SAC configuration and policy for enhanced performance 

- Updated standard deviation parameterization in SACConfig to 'softplus' with defined min and max values for improved stability.
- Modified action sampling in SACPolicy to use reparameterized sampling, ensuring better gradient flow and log probability calculations.
- Cleaned up log probability calculations in TanhMultivariateNormalDiag for clarity and efficiency.
- Increased evaluation frequency in YAML configuration to 50000 for more efficient training cycles.

These changes aim to enhance the robustness and performance of the SAC implementation during training and inference.
This commit is contained in:
KeWang1017 2024-12-28 22:11:34 +00:00 committed by Michel Aractingi
parent d1baa5a82f
commit 9ceb68ee90
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
lerobot/configs/policy/sac_pusht_keypoints.yaml
View File

@ -19,7 +19,7 @@ training:
grad_clip_norm: 10.0
lr: 3e-4
eval_freq: 10000
eval_freq: 50000
log_freq: 500
save_freq: 50000