Monte-Carlo Planning for Team Re-Formation Under Uncertainty: Model and Properties

Teamwork in decentralized systems plays a central role in recent artificial intelligence advances, such as in applications to disaster response. Decentralized partially observable Markov decision processes (Dec-POMDPs) have emerged as the de facto standard mathematical framework to study and optimal...

Full description

Saved in:
Bibliographic Details
Main Authors: Cohen, Jonathan, Mouaddib, Abdel-Illah
Format: Conference Proceeding
Language:English
Subjects:
Complexity theory
History
Monte Carlo methods
Monte-Carlo Tree Search
Multiagent systems
Planning
Planning under uncertainty
Task analysis
Team formation
Uncertainty
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Teamwork in decentralized systems plays a central role in recent artificial intelligence advances, such as in applications to disaster response. Decentralized partially observable Markov decision processes (Dec-POMDPs) have emerged as the de facto standard mathematical framework to study and optimally plan in sequentially decentralized multiagent systems under uncertainty. In this work, we focus our analysis on team formation and reformation in Decentralized POMDPs with a new model coined Team-POMDPs. We present some interesting structural properties of this model inherited from the field of cooperative game theory. We introduce a Monte Carlo-based planning algorithm to learn locally optimal team-reformation policies that tell our agents how to dynamically rearrange in order to better deal with the evolution of the task at hand. By reforming the team during execution, our experiments show that we are able to achieve higher expected long-term rewards than with stationary teams.
ISSN:2375-0197
DOI:10.1109/ICTAI.2018.00077