Multi-Objective Dynamic Dispatch Optimisation using Multi-Agent Reinforcement Learning: (Extended Abstract)

Patrick Mannion; Karl Mason; Sam Devlin; Jim Duggan; Enda Howley

Multi-Objective Dynamic Dispatch Optimisation using Multi-Agent Reinforcement Learning: (Extended Abstract)

Patrick Mannion, Karl Mason, Sam Devlin, Jim Duggan, Enda Howley

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, we examine the application of Multi-Agent Reinforcement Learning (MARL) to a Dynamic Economic Emissions Dispatch problem. This is a multi-objective problem domain, where the conflicting objectives of fuel cost and emissions must be minimised. We evaluate the performance of several different MARL credit assignment structures in this domain, and our experimental results show that MARL can produce comparable solutions to those computed by Genetic Algorithms and Particle Swarm Optimisation.

Original language	English
Title of host publication	Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems
Publisher	International Foundation for Autonomous Agents and Multiagent Systems
Pages	1345-1346
Number of pages	2
ISBN (Print)	978-1-4503-4239-1
Publication status	Published - 9 May 2016
Event	International Conference on Autonomous Agents & Multiagent Systems - Duration: 9 May 2016 → 13 May 2016

Conference

Conference	International Conference on Autonomous Agents & Multiagent Systems
Abbreviated title	AAMAS
Period	9/05/16 → 13/05/16

Access to Document

http://dl.acm.org/citation.cfm?id=2937152

Cite this

Mannion, P., Mason, K., Devlin, S., Duggan, J., & Howley, E. (2016). Multi-Objective Dynamic Dispatch Optimisation using Multi-Agent Reinforcement Learning: (Extended Abstract). In Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems (pp. 1345-1346). International Foundation for Autonomous Agents and Multiagent Systems . http://dl.acm.org/citation.cfm?id=2937152

@inproceedings{ff85bd7868a34e32b1210c7bdb316349,

title = "Multi-Objective Dynamic Dispatch Optimisation using Multi-Agent Reinforcement Learning: (Extended Abstract)",

abstract = "In this paper, we examine the application of Multi-Agent Reinforcement Learning (MARL) to a Dynamic Economic Emissions Dispatch problem. This is a multi-objective problem domain, where the conflicting objectives of fuel cost and emissions must be minimised. We evaluate the performance of several different MARL credit assignment structures in this domain, and our experimental results show that MARL can produce comparable solutions to those computed by Genetic Algorithms and Particle Swarm Optimisation.",

author = "Patrick Mannion and Karl Mason and Sam Devlin and Jim Duggan and Enda Howley",

year = "2016",

month = may,

day = "9",

language = "English",

isbn = "978-1-4503-4239-1",

pages = "1345--1346",

booktitle = "Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems",

publisher = "International Foundation for Autonomous Agents and Multiagent Systems ",

note = "International Conference on Autonomous Agents & Multiagent Systems, AAMAS ; Conference date: 09-05-2016 Through 13-05-2016",

}

Mannion, P, Mason, K, Devlin, S, Duggan, J & Howley, E 2016, Multi-Objective Dynamic Dispatch Optimisation using Multi-Agent Reinforcement Learning: (Extended Abstract). in Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems. International Foundation for Autonomous Agents and Multiagent Systems , pp. 1345-1346, International Conference on Autonomous Agents & Multiagent Systems, 9/05/16. <http://dl.acm.org/citation.cfm?id=2937152>

Multi-Objective Dynamic Dispatch Optimisation using Multi-Agent Reinforcement Learning: (Extended Abstract). / Mannion, Patrick; Mason, Karl; Devlin, Sam et al.
Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems. International Foundation for Autonomous Agents and Multiagent Systems , 2016. p. 1345-1346.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Multi-Objective Dynamic Dispatch Optimisation using Multi-Agent Reinforcement Learning

T2 - International Conference on Autonomous Agents & Multiagent Systems

AU - Mannion, Patrick

AU - Mason, Karl

AU - Devlin, Sam

AU - Duggan, Jim

AU - Howley, Enda

PY - 2016/5/9

Y1 - 2016/5/9

N2 - In this paper, we examine the application of Multi-Agent Reinforcement Learning (MARL) to a Dynamic Economic Emissions Dispatch problem. This is a multi-objective problem domain, where the conflicting objectives of fuel cost and emissions must be minimised. We evaluate the performance of several different MARL credit assignment structures in this domain, and our experimental results show that MARL can produce comparable solutions to those computed by Genetic Algorithms and Particle Swarm Optimisation.

AB - In this paper, we examine the application of Multi-Agent Reinforcement Learning (MARL) to a Dynamic Economic Emissions Dispatch problem. This is a multi-objective problem domain, where the conflicting objectives of fuel cost and emissions must be minimised. We evaluate the performance of several different MARL credit assignment structures in this domain, and our experimental results show that MARL can produce comparable solutions to those computed by Genetic Algorithms and Particle Swarm Optimisation.

M3 - Conference contribution

SN - 978-1-4503-4239-1

SP - 1345

EP - 1346

BT - Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems

PB - International Foundation for Autonomous Agents and Multiagent Systems

Y2 - 9 May 2016 through 13 May 2016

ER -