Co-authored-by: Khalil Meftah <kmeftah.khalil@gmail.com>
Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com>
Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co>
Co-authored-by: Ke Wang <superwk1017@gmail.com>
- Added Nan detection mechanisms in the actor, learner and gym_manipulator for the case where we encounter nans in the loop.
- changed the non-blocking in the `.to(device)` functions to only work for the case of cuda because they were causing nans when running the policy on mps
- Added some joint clipping and limits in the env, robot and policy configs. TODO clean this part and make the limits in one config file only.
Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com>
- Added `lerobot/scripts/server/find_joint_limits.py` to test the min and max angles of the motion you wish the robot to explore during RL training.
- Added logic in `manipulator.py` to limit the maximum possible joint angles to allow motion within a predefined joint position range. The limits are specified in the yaml config for each robot. Checkout the so100.yaml.
Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com>
- Added several wrappers around the base gym env robot class.
- Including: time limit, reward classifier, crop images, preprocess observations.
- Added an interactive script crop_roi.py where the user can interactively select the roi in the observation images and return the correct crop values that will improve the policy and reward classifier performance.
Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com>
- added `torch.compile` to the actor and learner servers.
- organized imports in `train_sac.py`
- optimized the parameters push by not sending the frozen pre-trained encoder.
Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com>
Added functions for converting the replay buffer from and to LeRobotDataset. When we want to save the replay buffer, we convert it first to LeRobotDataset format and save it locally and vice-versa.
Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com>
- Optimized critic design that improves the performance of the learner loop by a factor of 2
- Cleaned the code and fixed style issues
- Completed the config with actor_learner_config field that contains host-ip and port elemnts that are necessary for the actor-learner servers.
Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com>
- 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.
- 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.
- 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.
- 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.
Eugene Mironov
Michel Aractingi
Yoel
AdilZouitine
KeWang1017
KeWang