Communication is a key tool for facilitating multi-agent coordination in multi-agent systems. However, communication may incur a cost associated with the required bandwidth. This paper develop framework of Interactive Dynamic Influence Diagrams, treating both standard actions and communication as explicit choices that the decision maker must consider. The goal is to derive both action policies and communication policies that together optimize a global value function. We present a heuristic algorithm to compute communication policies by evaluating the trade-off between the cost of communication and the value of the information received. Finally, experimental results show the impact of communication policies have on the overall agent policies in the context of Multi-agent tiger problem.