Here is a question about applying multiple agents simutaneously when training using RL Toolbox.
Background: I have been trying to apply reinforcement learning method to multiagent control in which scenario communication between agents is required. So I need to train agents simultaneously while they exchange data/ message with each other，like states（observations）and reward.
According to my knowledge，there only can be one single RLagent in one Simulink file while creating environment. Besides，function ‘train’ seems not to support to train several agents simultaneously while using several Simulink files.
So how to solve this problem? Any suggestions would be really appreciated!
Best Answer