Investigating reinforcement learning in multiagent coalition formation

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

In this paper we investigate the use of reinforcement learning to address the multiagent coalition formation problem in dynamic, uncertain, real-time, and noisy environments. To adapt to the complex environmental factors, we equip each agent with the case-based reinforcement learning ability which is the integration of case-based reasoning and reinforcement learning. The agent can use case-based reasoning to derive a coalition formation plan in a real-time manner based on the past experience, and then instantiate the plan adapting to the dynamic and uncertain environment with the reinforcement learning on coalition formation experience. In this paper we focus on describing multiple aspects of the application of reinforcement learning in multiagent coalition formation. We classify two types of reinforcement learning: case-oriented reinforcement learning and peerrelated reinforcement learning, corresponding to strategic, off-line learning scenario and tactical, online learning scenario respectively. An agent might learn about the others' joint or individual behavior during coalition formation, as a result, we identify them as joint-behavior reinforcement learning and individual-behavior reinforcement learning. We embed the learning approach in a multi-phase coalition formation model and have implemented the approach.

Original languageEnglish (US)
Title of host publicationAAAI Workshop - Technical Report
Pages22-28
Number of pages7
VolumeWS-04-06
StatePublished - 2004
Event19th National Conference on Artificial Intelligence - San Jose, CA
Duration: Jul 25 2004Jul 26 2004

Other

Other19th National Conference on Artificial Intelligence
CitySan Jose, CA
Period7/25/047/26/04

Fingerprint

Reinforcement learning
Case based reasoning

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Li, X., & Soh, L-K. (2004). Investigating reinforcement learning in multiagent coalition formation. In AAAI Workshop - Technical Report (Vol. WS-04-06, pp. 22-28)

Investigating reinforcement learning in multiagent coalition formation. / Li, Xin; Soh, Leen-Kiat.

AAAI Workshop - Technical Report. Vol. WS-04-06 2004. p. 22-28.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, X & Soh, L-K 2004, Investigating reinforcement learning in multiagent coalition formation. in AAAI Workshop - Technical Report. vol. WS-04-06, pp. 22-28, 19th National Conference on Artificial Intelligence, San Jose, CA, 7/25/04.
Li X, Soh L-K. Investigating reinforcement learning in multiagent coalition formation. In AAAI Workshop - Technical Report. Vol. WS-04-06. 2004. p. 22-28
Li, Xin ; Soh, Leen-Kiat. / Investigating reinforcement learning in multiagent coalition formation. AAAI Workshop - Technical Report. Vol. WS-04-06 2004. pp. 22-28
@inproceedings{00879e136d5645c39903606b4e579237,
title = "Investigating reinforcement learning in multiagent coalition formation",
abstract = "In this paper we investigate the use of reinforcement learning to address the multiagent coalition formation problem in dynamic, uncertain, real-time, and noisy environments. To adapt to the complex environmental factors, we equip each agent with the case-based reinforcement learning ability which is the integration of case-based reasoning and reinforcement learning. The agent can use case-based reasoning to derive a coalition formation plan in a real-time manner based on the past experience, and then instantiate the plan adapting to the dynamic and uncertain environment with the reinforcement learning on coalition formation experience. In this paper we focus on describing multiple aspects of the application of reinforcement learning in multiagent coalition formation. We classify two types of reinforcement learning: case-oriented reinforcement learning and peerrelated reinforcement learning, corresponding to strategic, off-line learning scenario and tactical, online learning scenario respectively. An agent might learn about the others' joint or individual behavior during coalition formation, as a result, we identify them as joint-behavior reinforcement learning and individual-behavior reinforcement learning. We embed the learning approach in a multi-phase coalition formation model and have implemented the approach.",
author = "Xin Li and Leen-Kiat Soh",
year = "2004",
language = "English (US)",
volume = "WS-04-06",
pages = "22--28",
booktitle = "AAAI Workshop - Technical Report",

}

TY - GEN

T1 - Investigating reinforcement learning in multiagent coalition formation

AU - Li, Xin

AU - Soh, Leen-Kiat

PY - 2004

Y1 - 2004

N2 - In this paper we investigate the use of reinforcement learning to address the multiagent coalition formation problem in dynamic, uncertain, real-time, and noisy environments. To adapt to the complex environmental factors, we equip each agent with the case-based reinforcement learning ability which is the integration of case-based reasoning and reinforcement learning. The agent can use case-based reasoning to derive a coalition formation plan in a real-time manner based on the past experience, and then instantiate the plan adapting to the dynamic and uncertain environment with the reinforcement learning on coalition formation experience. In this paper we focus on describing multiple aspects of the application of reinforcement learning in multiagent coalition formation. We classify two types of reinforcement learning: case-oriented reinforcement learning and peerrelated reinforcement learning, corresponding to strategic, off-line learning scenario and tactical, online learning scenario respectively. An agent might learn about the others' joint or individual behavior during coalition formation, as a result, we identify them as joint-behavior reinforcement learning and individual-behavior reinforcement learning. We embed the learning approach in a multi-phase coalition formation model and have implemented the approach.

AB - In this paper we investigate the use of reinforcement learning to address the multiagent coalition formation problem in dynamic, uncertain, real-time, and noisy environments. To adapt to the complex environmental factors, we equip each agent with the case-based reinforcement learning ability which is the integration of case-based reasoning and reinforcement learning. The agent can use case-based reasoning to derive a coalition formation plan in a real-time manner based on the past experience, and then instantiate the plan adapting to the dynamic and uncertain environment with the reinforcement learning on coalition formation experience. In this paper we focus on describing multiple aspects of the application of reinforcement learning in multiagent coalition formation. We classify two types of reinforcement learning: case-oriented reinforcement learning and peerrelated reinforcement learning, corresponding to strategic, off-line learning scenario and tactical, online learning scenario respectively. An agent might learn about the others' joint or individual behavior during coalition formation, as a result, we identify them as joint-behavior reinforcement learning and individual-behavior reinforcement learning. We embed the learning approach in a multi-phase coalition formation model and have implemented the approach.

UR - http://www.scopus.com/inward/record.url?scp=32144445442&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=32144445442&partnerID=8YFLogxK

M3 - Conference contribution

VL - WS-04-06

SP - 22

EP - 28

BT - AAAI Workshop - Technical Report

ER -