pre-commit-ci[bot]
0ea27704f6
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2025-04-18 15:09:25 +02:00
pre-commit-ci[bot]
85fe8a3f4e
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2025-04-18 15:06:51 +02:00
Michel Aractingi
d2c41b35db
- 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 >
2025-04-18 15:04:13 +02:00
Michel Aractingi
508f5d1407
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 >
2025-04-18 15:04:13 +02:00
AdilZouitine
c8b1132846
Stable version of rlpd + drq
2025-04-18 15:04:10 +02:00
Adil Zouitine
760d60ad4b
Change SAC policy implementation with configuration and modeling classes
2025-04-18 15:03:51 +02:00
Adil Zouitine
875c0271b7
SAC works
2025-04-18 15:03:51 +02:00
Adil Zouitine
46827fb002
Add rlpd tricks
2025-04-18 15:03:51 +02:00
Adil Zouitine
2fd78879f6
SAC works
2025-04-18 15:03:51 +02:00
Adil Zouitine
a0e2be8b92
[WIP] correct sac implementation
2025-04-18 15:03:51 +02:00
