Home // INTELLI 2025, The Fourteenth International Conference on Intelligent Systems and Applications // View article

Situated Independent Learners in a Sequential Decision-Making Setting

Authors:
Timur Kasimov
Shinon Takei
Hanfeng Lu
Mingi Lee
Fernanda Eliott

Keywords: action shadowing; discrete actuator arrays; independent learners; sequential decision making.

Abstract:
Tricky coordination challenges can emerge from combining distributed settings with independent learners (since these learners have only access to limited information). Still, treating agents as independent learners can help mitigate the problem of observing multiple agents’ joint actions. Here, we detail and examine the Discrete Smart Surface benchmark with two goals: 1. Follow a call to the Multi-Agent Systems community to consider the environment as an important entity at the application level, and 2. Show/discuss our experimental results for combining independent learners with the Discrete Smart Sur- face benchmark under various dimensions and agent-weighting systems. Investigating challenges in Multi-Agent Systems can be particularly insightful for applications that rely on multiple decision-makers; thus, we thoroughly reflect on our experimental results and exemplify challenges, such as action shadowing.

Pages: 21 to 29

Copyright: Copyright (c) IARIA, 2025

Publication date: March 9, 2025

Published in: conference

ISSN: 2308-4065

ISBN: 978-1-68558-236-4

Location: Lisbon, Portugal

Dates: from March 9, 2025 to March 13, 2025