MAPDN
MAPDN copied to clipboard
Bug: Multiple actions per agent
I have identified a potential issue when trying to have multiple actions per agent.
In my example, I have 5 agents and 4 actions per agent, which means that the actions should have shape [1,5,4].
However, according to the error that I am getting, the shape of the actions is [1,1,4]. By debugging it, I found that in the function get_actions(self, state, status, exploration, actions_avail, target=False, last_hid=None)
of maddpg.py
the variable means
had the correct shape [1, 5, 4], but then the problem was due to the following part:
if means.size(-1) > 1:
means_ = means.sum(dim=1, keepdim=True)
log_stds_ = log_stds.sum(dim=1, keepdim=True)
else:
means_ = means
log_stds_ = log_stds
My question now is what is the purpose of this part?