Novelty seeking multiagent evolutionary reinforcement learning

Conference Paper (2023)
Author(s)

Ayhan Alp Aydeniz (Oregon State University)

Robert Loftin (TU Delft - Interactive Intelligence)

Kagan Tumer (Oregon State University)

Research Group
Interactive Intelligence
Copyright
© 2023 Ayhan Alp Aydeniz, R.T. Loftin, Kagan Tumer
DOI related publication
https://doi.org/10.1145/3583131.3590428
More Info
expand_more
Publication Year
2023
Language
English
Copyright
© 2023 Ayhan Alp Aydeniz, R.T. Loftin, Kagan Tumer
Research Group
Interactive Intelligence
Pages (from-to)
402-410
ISBN (electronic)
9798400701191
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Coevolving teams of agents promises effective solutions for many coordination tasks such as search and rescue missions or deep ocean exploration. Good team performance in such domains generally relies on agents discovering complex joint policies, which is particularly difficult when the fitness functions are sparse (where many joint policies return the same or even zero fitness values). In this paper, we introduce Novelty Seeking Multiagent Evolutionary Reinforcement Learning (NS-MERL), which enables agents to more efficiently explore their joint strategy space. The key insight of NS-MERL is to promote good exploratory behaviors for individual agents using a dense, novelty-based fitness function. Though the overall team-level performance is still evaluated via a sparse fitness function, agents using NS-MERL more efficiently explore their joint action space and more readily discover good joint policies. Our results in complex coordination tasks show that teams of agents trained with NS-MERL perform significantly better than agents trained solely with task-specific fitnesses.

Files

3583131.3590428.pdf
(pdf | 1.81 Mb)
- Embargo expired in 15-01-2024
License info not available