You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: mujoco_controllers/README.md
+8-2Lines changed: 8 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,12 +1,18 @@
1
1
# Running Controller Examples
2
2
3
-
Simply run python script for <controller.py>, for all the apple fan boys/girls run command as follows:
3
+
Simply run python scripts after activating poetry environment,
4
+
5
+
```
6
+
python <controller.py>
7
+
```
8
+
9
+
if you are on MacOS you will need to run the command as follows in order to load the interactive viewer:
4
10
5
11
```python
6
12
mjpython <controller.py>
7
13
```
8
14
9
-
See the following [discussion](https://github.com/google-deepmind/mujoco/discussions/780) for why this is required.
15
+
See the following [discussion](https://github.com/google-deepmind/mujoco/discussions/780) for further details on interactive viewer on MacOS.
10
16
11
17
# Tuning Controllers for Task Domain
12
18
I currently tune these controller implementations for each particular task environment. The reason for this is that each environment has different physics settings (timesteps etc.) and task requirements. My current approach is to use genetic algorithms for this tuning process, it remains far from perfect in its current form. I hope to open source environments and tuning setups for tasks in future.
0 commit comments