Michel Aractingi
b29401e4e2
- Refactor observation encoder in modeling_sac.py
...
- 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 >
2025-03-28 17:18:24 +00:00
Michel Aractingi
ef64ba91d9
Added server directory in lerobot/scripts that contains scripts and the protobuf message types to split training into two processes, acting and learning. The actor rollouts the policy and collects interaction data while the learner recieves the data, trains the policy and sends the updated parameters to the actor. The two scripts are ran simultaneously
...
Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com >
2025-03-28 17:18:24 +00:00
AdilZouitine
83dc00683c
Stable version of rlpd + drq
2025-03-28 17:18:24 +00:00
Adil Zouitine
4b78ab2789
Change SAC policy implementation with configuration and modeling classes
2025-03-28 17:18:24 +00:00
Adil Zouitine
bd8c768f62
SAC works
2025-03-28 17:18:24 +00:00
Adil Zouitine
921ed960fb
Add rlpd tricks
2025-03-28 17:18:24 +00:00
Adil Zouitine
67b64e445b
SAC works
2025-03-28 17:18:24 +00:00
Adil Zouitine
b495b19a6a
[WIP] correct sac implementation
2025-03-28 17:18:24 +00:00
