I am solving a multi agent problem where each agent has a critic and actor. The problem I am solving has discrete actions and discrete states. I came cross multi-agent deep deterministic policy gradient (MADDPG ) where each actor is trained using policy gradient. However, it is proposed fir continuous actions while I have discrete actions. I googled it but I did not find a reference where this MADDPG is used for discrete actions. I am new to the AI world and trying to build up my knowledge. Here is the link for the MADDPG



You must log in to answer this question.

Browse other questions tagged .