KeWang1017 5b4adc00bb Refactor SAC configuration and policy for improved action sampling and stability ...

- Updated SACConfig to replace standard deviation parameterization with log_std_min and log_std_max for better control over action distributions.
- Modified SACPolicy to streamline action selection and log probability calculations, enhancing stochastic behavior.
- Removed deprecated TanhMultivariateNormalDiag class to simplify the codebase and improve maintainability.

These changes aim to enhance the robustness and performance of the SAC implementation during training and inference.

2024-12-29 14:27:19 +00:00

..

act

fix(act): n_vae_encoder_layers config parameter wasn't being used (#400)

2024-09-02 18:29:27 +01:00

diffusion

feat: enable to use multiple rgb encoders per camera in diffusion policy (#484)

2024-10-30 11:00:05 +01:00

hilserl

Added normalization schemes and style checks

2024-12-29 12:51:21 +00:00

sac

Refactor SAC configuration and policy for improved action sampling and stability

2024-12-29 14:27:19 +00:00

tdmpc

Improve discoverability on the hub (#325)

2024-08-19 15:16:46 +02:00

vqbet

Bug: Fix VQ-Bet not working when n_action_pred_token=1 (#420)

2024-09-09 09:41:13 +01:00

factory.py

added optimizer and sac to factory.py

2024-12-23 14:12:03 +01:00

normalize.py

Make sure policies don't mutate the batch (#323)

2024-07-22 20:38:33 +01:00

policy_protocol.py

Improves Type Annotations (#252)

2024-06-10 19:09:48 +01:00

utils.py

Make policies compatible with other/multiple image keys (#149)

2024-05-16 13:51:53 +01:00