add FAQ to readme

README.md

@@ -139,6 +139,13 @@ To evaluate on your own environment, simply wrap it in a Gym interface and follo
 | Model Architecture  | [octo_module.py](octo/model/octo_module.py)             | Combines token sequencing, transformer backbone and readout heads.            |
 | Visualization       | [visualization_lib.py](octo/utils/visualization_lib.py) | Utilities for offline qualitative & quantitative eval.                        |
 
+## FAQ
+#### What is the `pad_mask` in the observation dictionary?
+The `pad_mask` indicates which observations should be attended to, which is important when using multiple timesteps of observation history. Octo was trained with a history window size of 2, meaning the model can predict an action using both the current observation and the previous observation. However, at the very beginning of the trajectory, there is no previous observation, so we need to set `pad_mask=False` at the corresponding index. If you use Octo with a window size of 1, pad_mask should always just be `[True]`, indicating that the one and only observation in the window should be attended to. Note that if you wrap your robot environment with the `HistoryWrapper` (see [gym_wrappers.py](octo/utils/gym_wrappers.py)), the `pad_mask` key will be added to the observation dictionary for you.
+#### What is `pad_mask_dict` in the observation dictionary?
+While `pad_mask` indicates which observations should be attended to on a timestep level, `pad_mask_dict` indicates which elements of the observation should be attended to within a single timestep. For example, for datasets without language labels, `pad_mask_dict["language_instruction"]` is set to `False`. For datasets without a wrist camera, `pad_mask_dict["image_wrist"]` is set to `False`. For convenience, if a key is missing from the observation dict, it is equivalent to setting `pad_mask_dict` to `False` for that key.
+#### Does `model.sample_actions([...])` return the full trajectory to solve a task?
+Octo was pretrained with an action chunking size of 4, meaning it predicts the next 4 actions at once. You can choose to execute all these actions before sampling new ones, or only execute the first action before sampling new ones (also known as receding horizon control). You can also do something more advanced like [temporal ensembling](octo/utils/gym_wrappers.py).
 
 ## Citation