CarolinePascal HF Staff commited on
Commit
ab769ee
·
verified ·
1 Parent(s): 71ecf44

fix(typos)

Browse files
app/src/content/chapters/folding/09-learnings.mdx CHANGED
@@ -28,10 +28,10 @@ If you're training a policy for a new manipulation task with LeRobot, **here's t
28
  python examples/rtc/eval_with_real_robot.py \
29
  --robot.type=bi_openarm_follower \
30
  --policy.path=outputs/checkpoints/last/pretrained_model \
31
- --device cuda \
32
- --rtc.enable=true \
33
  --rtc.execution_horizon=20 \
34
- --interpolation_multiplier=3`
35
  ```
36
 
37
  6. **Find the right [action representation](https://huggingface.co/docs/lerobot/action_representations).** LeRobot uses absolute actions by default. Switching to relative trajectory was one of our key improvements, and unlocked consistency with π0.5 pretraining. To enable relative actions for π0/π0.5 using LeRobot, first precompute the relative action statistics for your dataset, then train with the flag enabled:
 
28
  python examples/rtc/eval_with_real_robot.py \
29
  --robot.type=bi_openarm_follower \
30
  --policy.path=outputs/checkpoints/last/pretrained_model \
31
+ --policy.device=cuda \
32
+ --rtc.enabled=true \
33
  --rtc.execution_horizon=20 \
34
+ --interpolation_multiplier=3
35
  ```
36
 
37
  6. **Find the right [action representation](https://huggingface.co/docs/lerobot/action_representations).** LeRobot uses absolute actions by default. Switching to relative trajectory was one of our key improvements, and unlocked consistency with π0.5 pretraining. To enable relative actions for π0/π0.5 using LeRobot, first precompute the relative action statistics for your dataset, then train with the flag enabled: