borealisai / mtmfrl Goto Github PK

Not clear where in the code the mean action is chosen and the Boltzmann policy is updated.

Hello! Your work on MTMFQ has solved the heterogeneous agents problem, and I have learned a lot from it. However, I do not quite understand the implementation of Boltzmann exploration in the code.

Do you think my understanding of this is correct?

1. In the scenario configurations for the multibattle and multigather, the agents are allowed to attack within the group, that is, the attribution "attack_in_group" is set to True (or 1). Is there any insight into such a setting? This seems contrary to the description of the paper in Sec. 5 paragraph 2, where the setting requires the agents in the same group to be cooperative.
2. From the algorithm description, each agent will maintain a separate Q network (also target Q network), but in the implementation, it seems that a group of agents will share one Q network (also target Q network). Is there any insight into such a design?

Cannot find the file "spawn_ai" is imported from in train_battle.py in the multi battle folder