Inference-Based Deterministic Messaging For Multi-Agent Communication

Authors

  • Varun Bhatt University of Alberta
  • Michael Buro University of Alberta

Keywords:

Agent Communication

Abstract

Communication is essential for coordination among humans and animals. Therefore, with the introduction of intelligent agents into the world, agent-to-agent and agent-to-human communication becomes necessary. In this paper, we first study learning in matrix-based signaling games to empirically show that decentralized methods can converge to a suboptimal policy. We then propose a modification to the messaging policy, in which the sender deterministically chooses the best message that helps the receiver to infer the sender's observation. Using this modification, we see, empirically, that the agents converge to the optimal policy in nearly all the runs. We then apply this method to a partially observable gridworld environment which requires cooperation between two agents and show that, with appropriate approximation methods, the proposed sender modification can enhance existing decentralized training methods for more complex domains as well.

Downloads

Published

2021-05-18

How to Cite

Bhatt, V., & Buro, M. (2021). Inference-Based Deterministic Messaging For Multi-Agent Communication. Proceedings of the AAAI Conference on Artificial Intelligence, 35(13), 11228-11236. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17339

Issue

Section

AAAI Technical Track on Multiagent Systems