google-deepmind / google-deepmind/deepmind-research
First-person view in Mujoban
Open
- Dominant language
- Jupyter Notebook
- Stars
- 15.2k
- Forks
- 2.9k
- PR merge metrics
- No merged PRs in 30d
Description
I'm trying to get the first-person view in Mujoban as shown in [Beyond Tabula-Rasa](https://sites.google.com/view/modular-rl/), but see only the following elements in the state:
```
'pixel_layer', 'full_entity_layer', 'top_camera', 'walker/body_height', 'walker/end_effectors_pos', 'walker/joints_pos', 'walker/joints_vel', 'walker/orientation', 'walker/sensors_accelerometer', 'walker/sensors_gyro', 'walker/sensors_touch', 'walker/sensors_velocimeter', 'walker/world_zaxis'
```
The first three elements show only the top-down views. How can I get the first-person view as well?
Contributor guide
Assessment
This issue has not been assessed yet.