AdilZouitine 9ea79f8a76 Add storage device parameter to replay buffer initialization ...

- Specify storage device for replay buffer to optimize memory management

2025-04-18 15:04:58 +02:00

..

actor_server.py

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

2025-04-18 15:04:58 +02:00

buffer.py

Refactor ReplayBuffer with tensor-based storage and improved sampling efficiency

2025-04-18 15:04:58 +02:00

crop_dataset_roi.py

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

2025-04-18 15:04:44 +02:00

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.

2025-04-18 15:04:13 +02:00

gym_manipulator.py

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

2025-04-18 15:04:56 +02:00

hilserl_pb2_grpc.py

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

2025-04-18 15:04:56 +02:00

hilserl_pb2.py

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

2025-04-18 15:04:56 +02:00

hilserl.proto

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

2025-04-18 15:04:56 +02:00

learner_server.py

Add storage device parameter to replay buffer initialization

2025-04-18 15:04:58 +02:00

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.

2025-04-18 15:04:58 +02:00

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.

2025-04-18 15:04:58 +02:00