The University of Southampton
University of Southampton Institutional Repository

Experience-based Reinforcement Learning to Acquire Effective Behavior in a Multiagent Domain

Experience-based Reinforcement Learning to Acquire Effective Behavior in a Multiagent Domain
Experience-based Reinforcement Learning to Acquire Effective Behavior in a Multiagent Domain
Abstract. In this paper, we discuss Profit-sharing, an experience-based reinforcement learning approach (which is similar to a Monte-Carlo based reinforcement learning method) that can be used to learn robust and effective actions within uncertain, dynamic, multi-agent systems. We introduce the cut-loop routine that discards looping behavior, and demonstrate its effectiveness empirically within a simplified NEO (non-combatant evacuation operation) domain. This domain consists of several agents which ferry groups of evacuees to one of several shelters. We demonstrate that the cut-loop routine makes the Profit-sharing approach adaptive and robust within a dynamic and uncertain domain, without the need for pre-defined knowledge or subgoals. We also compare it empirically with the popular Q-learning approach.
125-135
Arai, Sachiyo
a9b81f3c-9110-4657-aa2d-e6acd75adfec
Sycara, Katia
df200c43-d34d-4093-bb4e-493fea2d0732
Payne, Terry R.
09574f42-3cbc-43d3-86c2-2f96eb6319a0
Arai, Sachiyo
a9b81f3c-9110-4657-aa2d-e6acd75adfec
Sycara, Katia
df200c43-d34d-4093-bb4e-493fea2d0732
Payne, Terry R.
09574f42-3cbc-43d3-86c2-2f96eb6319a0

Arai, Sachiyo, Sycara, Katia and Payne, Terry R. (2000) Experience-based Reinforcement Learning to Acquire Effective Behavior in a Multiagent Domain. The Sixth Pacific Rim International Conference on Artificial Intelligence (PRICAI 2000). pp. 125-135 .

Record type: Conference or Workshop Item (Paper)

Abstract

Abstract. In this paper, we discuss Profit-sharing, an experience-based reinforcement learning approach (which is similar to a Monte-Carlo based reinforcement learning method) that can be used to learn robust and effective actions within uncertain, dynamic, multi-agent systems. We introduce the cut-loop routine that discards looping behavior, and demonstrate its effectiveness empirically within a simplified NEO (non-combatant evacuation operation) domain. This domain consists of several agents which ferry groups of evacuees to one of several shelters. We demonstrate that the cut-loop routine makes the Profit-sharing approach adaptive and robust within a dynamic and uncertain domain, without the need for pre-defined knowledge or subgoals. We also compare it empirically with the popular Q-learning approach.

PDF
pricai2000.pdf - Other
Download (270kB)

More information

Published date: 2000
Venue - Dates: The Sixth Pacific Rim International Conference on Artificial Intelligence (PRICAI 2000), 2000-01-01
Organisations: Electronics & Computer Science

Identifiers

Local EPrints ID: 257790
URI: https://eprints.soton.ac.uk/id/eprint/257790
PURE UUID: 8dfcafb1-03cf-4e26-9fdb-fa46a8539726

Catalogue record

Date deposited: 24 Jun 2003
Last modified: 18 Jul 2017 09:35

Export record

Contributors

Author: Sachiyo Arai
Author: Katia Sycara
Author: Terry R. Payne

University divisions

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of https://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×