hangX/lerobot
1
0
Fork 0
forked from tangger/lerobot
Code Pull Requests Activity

FREEDOM, added back the optimization loop code in learner_server.py

Browse Source 
Ran experiment with pushcube env from maniskill. The learning seem to work.

Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com>
This commit is contained in:
Michel Aractingi
2025-01-28 17:25:49 +00:00
parent 508f5d1407
commit 2ae657f568
3 changed files with 85 additions and 80 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
lerobot/configs/policy/sac_manyskill.yaml
View File

@@ -82,7 +82,7 @@ policy:
temperature_lr: 3e-4
# critic_target_update_weight: 0.005
critic_target_update_weight: 0.01
utd_ratio: 1
utd_ratio: 2
# # Loss coefficients.