AdilZouitine 5b4a7aa81d Add storage device parameter to replay buffer initialization ...

- Specify storage device for replay buffer to optimize memory management

2025-02-25 15:30:39 +00:00

..

actor_server.py

Update ManiSkill configuration and replay buffer to support truncation and dataset handling

2025-02-24 16:53:37 +00:00

buffer.py

Refactor ReplayBuffer with tensor-based storage and improved sampling efficiency

2025-02-25 14:26:44 +00:00

crop_dataset_roi.py

Fixed bug in the action scale of the intervention actions and offline dataset actions. (scale by inverse delta)

2025-02-14 15:17:16 +01:00

find_joint_limits.py

- Added JointMaskingActionSpace wrapper in gym_manipulator in order to select which joints will be controlled. For example, we can disable the gripper actions for some tasks.

2025-02-11 11:34:46 +01:00

gym_manipulator.py

[Port HIL-SERL] Adjust Actor-Learner architecture & clean up dependency management for HIL-SERL (#722)

2025-02-21 10:29:00 +01:00

hilserl_pb2_grpc.py

[Port HIL-SERL] Adjust Actor-Learner architecture & clean up dependency management for HIL-SERL (#722)

2025-02-21 10:29:00 +01:00

hilserl_pb2.py

[Port HIL-SERL] Adjust Actor-Learner architecture & clean up dependency management for HIL-SERL (#722)

2025-02-21 10:29:00 +01:00

hilserl.proto

[Port HIL-SERL] Adjust Actor-Learner architecture & clean up dependency management for HIL-SERL (#722)

2025-02-21 10:29:00 +01:00

learner_server.py

Add storage device parameter to replay buffer initialization

2025-02-25 15:30:39 +00:00

learner_service.py

Added caching function in the learner_server and modeling sac in order to limit the number of forward passes through the pretrained encoder when its frozen.

2025-02-21 10:13:43 +00:00

maniskill_manipulator.py

Added caching function in the learner_server and modeling sac in order to limit the number of forward passes through the pretrained encoder when its frozen.

2025-02-21 10:13:43 +00:00