oxwhirl/smac

Are the state transition function and reward function stochastic?

starry-sky6688 opened this issue · 1 comments

Hi, I'm wordering about the dynamic of this environment, are the state transition function and reward function stochastic?

Looking forward to your reply!

Hi @starry-sky6688 ,

The transition function of the environment is indeed stochastic. cooldown, for example, which is the time
that the agents need to wait until being able to shoot again, is probabilistic. The reward function is deterministic.