What to Communicate? Execution-time Decision in Multi-agent POMDPs

Maayan Roth, Reid Simmons and Manuela Veloso
Conference Paper, The 8th International Symposium on Distributed Autonomous Robotic Systems (DARS), January, 2006


Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

In recent years, multi-agent Partially Observable Markov Decision Processes (POMDP) have emerged as a popular decision-theoretic framework for modeling and generating policies for the control of multi-agent teams. Teams controlled by multi-agent POMDPs can use communication to share observations and coordinate. Therefore, policies are needed to enable these teams to reason about communication. Previous work on generating communication policies for multi-agent POMDPs has focused on the question of when to communicate. In this paper, we address the question of what to communicate. We describe two paradigms for representing limitations on communication and present an algorithm that enables multi-agent teams to make execution-time decisions on how to effectively utilize available communication resources.


@conference{Roth-2006-17008,
author = {Maayan Roth and Reid Simmons and Manuela Veloso},
title = {What to Communicate? Execution-time Decision in Multi-agent POMDPs},
booktitle = {The 8th International Symposium on Distributed Autonomous Robotic Systems (DARS)},
year = {2006},
month = {January},
} 2017-09-13T10:42:59-04:00