Michel Aractingi ff47c0b0d3 - Fixed big issue in the loading of the policy parameters sent by the learner to the actor -- pass only the actor to the `update_policy_parameters` and remove `strict=False` ... - Fixed big issue in the normalization of the actions in the `forward` function of the critic -- remove the `torch.no_grad` decorator in `normalize.py` in the normalization function - Fixed performance issue to boost the optimization frequency by setting the storage device to be the same as the device of learning. Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com>		2025-02-19 16:22:51 +00:00
..
env	Add maniskill support.	2025-02-14 19:53:29 +00:00
policy	- Fixed big issue in the loading of the policy parameters sent by the learner to the actor -- pass only the actor to the `update_policy_parameters` and remove `strict=False`	2025-02-19 16:22:51 +00:00
robot	Changed bounds for a new so100 robot	2025-02-13 15:43:30 +01:00
default.yaml	Several fixes to move the actor_server and learner_server code from the maniskill environment to the real robot environment.	2025-02-10 16:03:39 +01:00