-
I am new to Unity and have installed it on my laptop. I am currently using 2017.4.34 version of Unity.
I have clearly followed the documentation for installation given on the github page and wheneve…
-
Hi,
I implement my own environment to the gym, and I want to train the baseline model DQN. However, I meet the issue of action size -- The environment was expecting **`action` to be a list**.
He…
-
How do you solve this issue @kotogasy
-
I had incredible difficulty setting up an environment for the ml agents, being new to Python (I have done C# and Unity stuff for around a decade)
For example, non python scripters don't know to not i…
-
Is there any way to look into the architecture of the neural net being trained and then reconfiguring the parameters according to our requirement in order to achieve better results. I know that frozen…
-
hi all,
when using tensorflow_to_barracuda.py , with either a mobilenet_v2.pb or inception.pb model file I get either
`assert x.data.size == np.prod(shape)
AssertionError`
with inception,
o…
-
Hi everyone,
We have released ML-Agents v0.15.0 on March 18th.
If you've been following the development of ML-Agents, you have probably noticed a lot of changes in recent months. We are proud to…
-
The `MLAgents.Agent` is a MonoBehaviour, which includes private functions like `OnEnable` and `OnDisable` that always have be called, yet it's possible for the user to implement their own new private …
-
Hello,
currently, I trained with both --slow and --fast (or not specified) and I found some different behavior.
firstly, I trained my agent with --slow option ( max steps = 1500 )
while trainin…
-