A Unity ID allows you to buy and/or subscribe to Unity products and services, shop in the Asset Store and participate in the Unity community.
Separate names with a comma.
@ruoping_unity Thank you for your reply. I still don't really understand why the environment would freeze for so long, even though it is not using...
Hello, I'm having a problem with SAC training but only when I'm working with behavioral cloning. Normal SAC training takes 25-30 minutes to finish...
Are you looking at the graphs only and picking the runs with the highest consistent rewards? Or do you look at the last reward only?
@mbaske Looks good. I see you're using the values that get generated in TensorBoard. I found something weird when it comes to the timers.json file...
@mbaske Sounds cool, please let me know in this thread if you manage to finish updating your project :)
Hello, I have been experimenting with the PushBlock example and different configuration files for it. The learning however looks a bit weird,...
@mbaske When you were running your hyperparameter tuner, was the whole process taking a long time? I mean, if I were to test many different...
So essentially, if I prepare some configs and I run the learning process through an executable (I can then launch all processes one by one), I...
Hi there, Is there a good method to tune the hyperparameters using ML-Agents. I know the docs suggest some of the values and I can just try out...
Hello! I wanted to do some experiments with the SAC algorithm and Behavioral Cloning, however, the official docs only mention PPO when it comes...
Hi there! Do you have any news on this matter? :)
Hi @andrewcoh_unity Thank you so much for your response! I have noticed two other things: 1. When I tried to use the models made by Unity,...
Hello! So I have been following the article below to learn more about this WallJump example...
Hello, I have a problem with learning my agents in the Karting Microgame. They pretty much have no problem with going through a flat track, left...
I think I found the issue. Agents do not have "idle" as an action - they either go forward or brake/go backwards. This is why in Heuristic...
Okay I changed the following: void InterpretDiscreteActions(float[] actions) { m_Steering = actions[0]; m_Brake =...
Now the car goes forward by itself, still steering right (@Edit - left, sorry) o_O I noticed that currently I am using both Agent and IInput...
That's okay, thank you for the quick responses :) I have tried the mapping like above and the errors are gone but once again, the agent is still...
I already have two branches with 3 actions per branch [ATTACH] Again, as this is a microgame, this was already prepared like this so I'm not...
I have just did that and the error was gone but after hitting Play, I got hundreds of errors like this: [ATTACH]