MAVEN: Multi-Agent Variational Exploration

However, two key challenges stand between cooperative MARL and such real-world applications. First, scalability is limited by the fact that the size of the joint action space grows exponentially in the number of agents. Second, while the training process can typically be centralised, partial observability and communication constraints often mean that execution must be decentralised, i.e., each agent can condition its actions only on its local action-observation history, a setting known as centralised