google-deepmind / google-deepmind/open_x_embodiment

Unsuccessful Episodes in the "fractal20220817_data"

Open
#45 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
2k
Forks
127
PR merge metrics
No merged PRs in 30d

Description

Hi! I have found some unsuccessful episodes in the `fractal20220817_data` dataset. I am saying that the robot could not complete the task.

For example, there are only **2** steps in #436 (start from 0) episode.

Task instruction:

```python
tf.Tensor(b'place pepsi can into bottom drawer', shape=(), dtype=string)
```

Step 0:

Terminate:

```python
tf.Tensor([1 0 0], shape=(3,), dtype=int32)
```

Image:

![episode_436_step_0](https://github.com/google-deepmind/open_x_embodiment/assets/55993100/eeee6ba8-7e5e-4af0-ab75-c68fed03ee14)

Step 1:

Terminate:

```python
tf.Tensor([0 0 0], shape=(3,), dtype=int32)
```

Image:

![episode_436_step_1](https://github.com/google-deepmind/open_x_embodiment/assets/55993100/6d302ecb-edbb-4d3e-ad90-2f3d4bf10a78)

Any explanation? Any idea for filtering such episodes?

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.