-
I am trying to find the Mujoco environments described in the DDPG paper in section 9.2: https://arxiv.org/pdf/1509.02971.pdf
I did find some in gym/envs/mujoco/, but not all of them. I wonder if th…
-
-
# MuJoCO
- [x] Get MuJoCo installed and running
- [x] Run through an Ant sample from elsewhere
- [ ] Tweak the model to learn the format
- [x] Read MuJoCo docs
- [ ] Add one constraint
- [ ] Add…
-
Hi, I'm trying to replicate your result, however the code not running well in my python 3.5 + macos, for example, multproccing I got EOF Error, I have fixed many this kind of error but I'm not sure ho…
-
I'm loading a custom MuJoCo environment and I want to run the viewer without defining a RL environment and task. Below is the way I load the XML file:
```
MODEL_PATH = PATH + '/models/data_collect…
-
Hi,
In the DeepMind Control Suite paper, Cart-pole has the dimension of (state_dimension=4, action_dimension=1, obervation_dimension=5). However, when I print the state dimension, I have more than …
ghost updated
5 years ago
-
```python
import numpy as np
from dm_control import suite
env = suite.load('reacher', 'easy')
action_spec = env.action_spec()
time_step = env.reset()
while not time_step.last():
print(time_…
-
Why is the position in cheetah is of dim 8 but the velocity is of dim 9? And what do they denote?
Are they 3d position of joints? Documentation of observation for all the environments would be very h…
-
I tried to install dm_control by pip install git+git://github.com/deepmind/dm_control.git.
However, I can import dm_control successfully, but when I used 'from dm_control import suite', error came.
…
-
I updated dm_control(with viewer...) today.But when I run sample code in Quickstart, the error comes again.
```python
>>> from dm_control import suite
>>> import numpy as np
>>>
>>> # Load one…