Principled Learning-to-Communicate with Quasi-Classical Information Structures

ArXi:2603.03664v2 Announce Type: replace-cross Learning-to-communicate (LTC) in partially observable environments has received increasing attention in deep multi-agent reinforcement learning, where the control and communication strategies are jointly learned. Meanwhile, the impact of communication on decision-making has been extensively studied in control theory. In this paper, we seek to formalize and better understand LTC by bridging these two lines of work, through the lens of information structures (ISs