Getting sac to work --- WIP #599
Open
+296
−123
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…_25_reshape_dataset
…_25_reshape_dataset
…_25_reshape_dataset
…_25_reshape_dataset
…_25_reshape_dataset
…_25_reshape_dataset
Co-authored-by: Daniel Ritchie <[email protected]> Co-authored-by: resolver101757 <[email protected]> Co-authored-by: Jannik Grothusen <[email protected]> Co-authored-by: Remi <[email protected]> Co-authored-by: Michel Aractingi <[email protected]>
…licy on the robot (huggingface#541) Co-authored-by: Yoel <[email protected]>
Co-authored-by: Yoel <[email protected]>
Co-authored-by: KeWang1017 <[email protected]>
…ing 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.
…1-27-port-hil-serl' into new_port_serl
- Increased `latent_dim` from 50 to 128 for improved representation. - Separated encoders for critic and actor in `SACPolicy` to enhance model performance. - Updated action selection method to use distribution mode for better inference. - Refactored critic forward pass to streamline Q-value calculations. - Improved temperature loss calculation and added comments for clarity. - Updated YAML configuration to switch observation type for keypoints evaluation. These changes aim to enhance the flexibility, performance, and clarity of the SAC implementation.
…n handling - Updated action selection to use distribution sampling and log probabilities for better stochastic behavior. - Enhanced standard deviation clamping to prevent extreme values, ensuring stability in policy outputs. - Cleaned up code by removing unnecessary comments and improving readability. These changes aim to refine the SAC implementation, enhancing its robustness and performance during training and inference.
- 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.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What this does
Try to get the sac running without errors. Several places made to improve:
SACPolicyto enhance model performance.How it was tested
python scripts/train.py policy=sac_pusht_keypoints env=pusht +dataset=lerobot/pusht_keypoints