Hi,
I have a question regarding the python API. I am trying to get the total number of agents for my own algorithm. I try to just add the length of decision steps and terminal steps to get the total number of agents in the beginning:
env.reset()
for brain in env.behavior_specs:
decision_steps, terminal_steps = env.get_steps(brain)
num_agents = len(decision_steps) + len(terminal_steps)
But somehow I get 24 decision steps and 1 terminal step(=25), although I only have 24 agents in the environment, even though I also called env.reset() before.
What am I missing?