• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
Balancing Individual Preferences and Shared Objectives in Multiagent Reinforcement Learning.
Ishan
Durugkar, Elad Liebman, and Peter
Stone.
In Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI 2020), July
2020.
15-minute presentation
In multiagent reinforcement learning scenarios, it is often the case that independent agents must jointly learn to perform a cooperative task. This paper focuses on such a scenario in which agents have individual preferences regarding how to accomplish the shared task. We consider a framework for this setting which balances individual preferences against task rewards using a linear mixing scheme. In our theoretical analysis we establish that agents can reach an equilibrium that leads to optimal shared task reward even when they consider individual preferences which are not fully aligned with this task. We then empirically show, somewhat counter-intuitively, that there exist mixing schemes that outperform a purely task-oriented baseline. We further consider empirically how to optimize the mixing scheme.
@InProceedings{IJCAI20-ishand,
author = {Ishan Durugkar and Elad Liebman and Peter Stone},
title = {Balancing Individual Preferences and Shared Objectives in
Multiagent Reinforcement Learning},
booktitle = {Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI 2020)},
location = {Yokohama Japan},
month = {July},
year = {2020},
abstract = {
In multiagent reinforcement learning scenarios, it is often the case that
independent agents must jointly learn to perform a cooperative task.
This paper focuses on such a scenario in which agents have individual
preferences regarding how to accomplish the shared task. We consider
a framework for this setting which balances individual preferences
against task rewards using a linear mixing scheme. In our
theoretical analysis we establish that agents can reach an
equilibrium that leads to optimal shared task reward even when they
consider individual preferences which are not fully aligned with this
task. We then empirically show, somewhat counter-intuitively, that
there exist mixing schemes that outperform a purely task-oriented
baseline. We further consider empirically how to optimize the mixing
scheme.
},
wwwnote={<a href="https://drive.google.com/file/d/1MkJBfx-qoESPPF6ZC1ZhH-1uXzp63lgK/view?usp=sharing">
15-minute presentation</a>},
}
Generated by bib2html.pl (written by Patrick Riley ) on Wed Apr 17, 2024 18:42:52