Adjust the timestamps' description in Diffusion Policy (#343)

Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
This commit is contained in:
Halvard Bariller 2024-07-26 13:47:03 +02:00 committed by GitHub
parent f8a6574698
commit 7a3cb1ad34
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions

View File

@ -111,12 +111,12 @@ class DiffusionPolicy(nn.Module, PyTorchModelHubMixin):
Schematically this looks like:
----------------------------------------------------------------------------------------------
(legend: o = n_obs_steps, h = horizon, a = n_action_steps)
|timestep | n-o+1 | n-o+2 | ..... | n | ..... | n+a-1 | n+a | ..... |n-o+1+h|
|observation is used | YES | YES | YES | NO | NO | NO | NO | NO | NO |
|timestep | n-o+1 | n-o+2 | ..... | n | ..... | n+a-1 | n+a | ..... | n-o+h |
|observation is used | YES | YES | YES | YES | NO | NO | NO | NO | NO |
|action is generated | YES | YES | YES | YES | YES | YES | YES | YES | YES |
|action is used | NO | NO | NO | YES | YES | YES | NO | NO | NO |
----------------------------------------------------------------------------------------------
Note that this means we require: `n_action_steps < horizon - n_obs_steps + 1`. Also, note that
Note that this means we require: `n_action_steps <= horizon - n_obs_steps + 1`. Also, note that
"horizon" may not the best name to describe what the variable actually means, because this period is
actually measured from the first observation which (if `n_obs_steps` > 1) happened in the past.
"""