Myopic and Non-myopic Communication under Partial Observability

摘要

In decentralized settings with partial observability, agents can often benefit from communicating, but communication resources may be limited and costly. Current approaches tend to dismiss or underestimate this cost, resulting in over-communication. This paper presents a general framework to compute the value of communicating from each agent’s local perspective, by comparing the expected reward with and without communication. In order to obtain these expectations, each agent must reason about the state and belief states of the other agents, both before and after communication. We show how this can be done in the context of decentralized POMDPs and discuss ways to mitigate a common myopic assumption, where agents tend to over-communicate because they overlook the possibility that communication can be deferred or initiated by the other agents. The paper presents a theoretical framework to precisely quantify the value of communication and an effective algorithm to manage communication. Experimental results show that our approach performs well compared to other techniques suggested in the literature.