Wait a Second! How Delays Disrupt Optimal Policies

Authors

  • Sarah Dumnich Saint Vincent College
  • Britton Wolfe Grove City College

DOI:

https://doi.org/10.32473/flairs.38.1.138917

Keywords:

Multi-Agent, Distributed Systems, Reinforcement Learning

Abstract

Communication delays can lead to inconsistent views of the world among the different agents. We prove that an optimal policy in a system with instant communication can be suboptimal when the same system exhibits communication delay.

Downloads

Published

14-05-2025

How to Cite

Dumnich, S., & Wolfe, B. (2025). Wait a Second! How Delays Disrupt Optimal Policies . The International FLAIRS Conference Proceedings, 38(1). https://doi.org/10.32473/flairs.38.1.138917