-
I want to set the Graph model through a script. So the agents trigger something I want to change their behavior. I know I have to access to this public variable, but I was not able to do it:
https:/…
-
Hi,
I am trying to run the gym wrapper of ml-agents. I installed ml-agents release 1 from source. Then I went into the gym-unity folder and installed gym unity with:
`pip3 install -e .`
Unfortuna…
-
**Describe the bug**
When I resumed training with --load the reward decreased to even lower than the inital reward
This is the command that I used for starting the training
```bash
mlagents-lea…
-
Hello,
what's the equivalent approach to run a Unity build in inference mode, while the interaction is done via mlagents.envs.
In v0.10.0 this was done by setting an argument during reset `env.r…
-
When I run the train command (as below) and click the player button in unity editor:
$mlagents-learn config/trainer_config.yaml --curriculum config/curricula/penguin --run-id penguin_01 --train
The …
-
I was trying out the simple RollerBall project with ml agents.
When I run ML agents v0.15.1 & ML agents v0.15.0, there appears to have errors as I type in
`mlagents-learn config/config.yaml --run…
-
Just updated to version 0.8, and I'm getting this error from the MLAgents.Agent.OnEnable(). I am enabling the academy and adding the agents with brains at runtime so that may be contributing to the is…
-
I tried Sample program(3D Ball) along the getting start guide.
But an error occurred...
```
Traceback (most recent call last):
File "c:\users\sobassy\anaconda3\lib\site-packages\mlagents\trainer…
-
**Hi, first of all i want to explain my goal:**
what i'm trying to do is making an example that can establish a connection between unity and python in order to exchange messages. Because after that …
-
After 92k steps an agent training to copy a demonstration starts to report:
WARNING:mlagents_envs:An agent had a NaN observation in the environment
and show this in tensorboard:
![image](https://us…