Heterogeneity: Based on the heterogeneity of agents MAS can be divided into two categories namely: homogeneous and heterogeneous. Homogeneous MAS include agents that all have the same characteristics and functionalities, while heterogeneous MAS include agents with diverse features.
As I read in this paper that these methods can deal with the heterogeneity of agents MAS : The dueling double deep Q-network (DDDQN) and Independent Deep Q-Network (IDQN): first approach to address heterogeneous multi-agent learning in urban traffic control. deep Q-network (DQN): To handle heterogeneity, each agent has different experience replay memory and different network policy. The asynchronous advantage actor-critic (A3C) algorithm is used to learn optimal policy for each agent, which can be extended to multiple heterogeneous agents. So, Can someone tell me What is the best method to deal with heterogeneous multi-agent system MAS?