google-deepmind / google-deepmind/deepmind-research

First-person view in Mujoban

Open
#296 0 comments 0 reactions 0 assignees View on GitHub
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

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.