Open kevupton opened 6 years ago
Hello @kevupton and sorry for the late response. I was traveling a lot in recent days and had very bad connectivity and few time. Your question refers to the simulation/environment implementation. I recommend keeping the solver decoupled from this, since the solver lives inside the world/environment/simulation.
Do you agree with me here? The example application learning-agents shows how this implementation could look like.
Hey,
This is more a question, but how would a termination scenario be handled in the case for a example, the game is over and needs to be restarted ?
If this is not implemented, do you have an idea of how it would be ?