How to ensure that the episode_len value remains unchanged when collecting data from multiple episodes of a task?

MarkFzp / act-plus-plus

Imitation learning algorithms with Co-training for Mobile ALOHA: ACT, Diffusion Policy, VINN

https://mobile-aloha.github.io/

MIT License

2.86k stars 525 forks source link

How to ensure that the episode_len value remains unchanged when collecting data from multiple episodes of a task? #42

Closed niovl closed 3 months ago

niovl commented 4 months ago

For example, in task aloha_mobile_wash_pan: in 50 episodes, episode_len=1099. How to ensure that the length of the episodes remains unchanged? Are there some requirements for the teacher's operation, or are the collection results truncated? Hope to receive your answer, thx.

asasarkaya commented 3 months ago

Hi, I was wondering about the same question. Did you figure this out?

niovl commented 2 months ago

Hi, I was wondering about the same question. Did you figure this out?

https://github.com/MarkFzp/act-plus-plus/blob/main/truncate_data.py，maybe it can help you