Loading [a11y]/accessibility-menu.js
Hurts to Be Too Early: Benefits and Drawbacks of Communication in Multi-Agent Learning | IEEE Conference Publication | IEEE Xplore

Hurts to Be Too Early: Benefits and Drawbacks of Communication in Multi-Agent Learning


Abstract:

We study a multi-agent partially observable environment in which autonomous agents aim to coordinate their actions, while also learning the parameters of the unknown envi...Show More

Abstract:

We study a multi-agent partially observable environment in which autonomous agents aim to coordinate their actions, while also learning the parameters of the unknown environment through repeated interactions. In particular, we focus on the role of communication in a multi-agent reinforcement learning problem. We consider a learning algorithm in which agents make decisions based on their own observations of the environment, as well as the observations of other agents, which are collected through communication between agents. We first identify two potential benefits of this type of information sharing when agents' observation quality is heterogeneous: (1) it can facilitate coordination among agents, and (2) it can enhance the learning of all participants, including the better informed agents. We show however that these benefits of communication depend in general on its timing, so that delayed information sharing may be preferred in certain scenarios.
Date of Conference: 29 April 2019 - 02 May 2019
Date Added to IEEE Xplore: 17 June 2019
ISBN Information:

ISSN Information:

Conference Location: Paris, France

Contact IEEE to Subscribe

References

References is not available for this document.