Enhance SAC configuration and policy with new parameters and subsampling logic

- Added `num_subsample_critics`, `critic_target_update_weight`, and `utd_ratio` to SACConfig.
- Implemented target entropy calculation in SACPolicy if not provided.
- Introduced subsampling of critics to prevent overfitting during updates.
- Updated temperature loss calculation to use the new target entropy.
- Added comments for future UTD update implementation.

These changes improve the flexibility and performance of the SAC implementation.

lerobot/common/policies/sac/configuration_sac.py

@@ -23,8 +23,11 @@ class SACConfig:
     discount = 0.99
     temperature_init = 1.0
     num_critics = 2
+    num_subsample_critics = None
     critic_lr = 3e-4
     actor_lr = 3e-4
+    critic_target_update_weight = 0.005
+    utd_ratio = 2
     critic_network_kwargs = {
             "hidden_dims": [256, 256],
             "activate_final": True,