If you have your environment set up correctly my interpretation is that you should do something
env = MyEnv()
policy = RandomPolicy() # Or whichever policy you want
s = state(env)
r = reward(env)
a = action(policy, r, s, actions(env, s))
new_r, new_s = step!(env, s, a)
I don’t really feel I have time for taking on that at the moment, but I’m sure you will figure it out. If you have questions you can always ask here and I will peek in every now and then.