Join GitHub today
GitHub is home to over 28 million developers working together to host and review code, manage projects, and build software together.Sign up
How to handle dynamic amount of states? #139
At first I wanted to thank you for this great ML-pipeline, playing around with it is really great!
So, what I’ve noticed is that agents have a list of states with a fixed size, which is ok when you have a constant environment like 1 ball and 1 platform which tries to keep the ball on it or in my case you have a platform and a pong-like ball.
But how about having enemies which spawn dynamically? Or when these enemies shoot bullets? We’d need a dynamic list of states for that or pre-define a list of states which can be filled up as needed. How would you implement this scenario?
As it currently stands, you are right that the state size needs to be fixed. In the case of dynamic number of enemies, one way to deal with this is to send only information about the