Michel Aractingi b5fbeb7401 Optimized the replay buffer from the memory side to store data on cpu instead of a gpu device and send the batches to the gpu. ...

Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com>

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

..

actor_server.py

nit

2025-04-18 15:04:43 +02:00

buffer.py

Optimized the replay buffer from the memory side to store data on cpu instead of a gpu device and send the batches to the gpu.

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

crop_dataset_roi.py

Changed bounds for a new so100 robot

2025-04-18 15:04:43 +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

Changed the init_final value to center the starting mean and std of the policy

2025-04-18 15:04:43 +02:00

hilserl.proto

- Added additional logging information in wandb around the timings of the policy loop and optimization loop.

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

learner_server.py

Hardcoded some normalization parameters. TODO refactor

2025-04-18 15:04:43 +02:00