Learning to select a co-ordination mechanism
Learning to select a co-ordination mechanism
This paper examines the potential and the impact of introducing learning capabilities into autonomous agents that make decisions at run-time about which mechanism to exploit in order to coordinate their activities. Specifically, the efficacy of learning is evaluated for making the decisions that are involved in determining when and how to coordinate. Our motivating hypothesis is that to deal with dynamic and unpredictable environments it is important to have agents that can learn the right situations in which to attempt to coordinate and the right method to use in those situations. This hypothesis is evaluated empirically, using reinforcement based algorithms, in a grid-world scenario in which a) an agent's prediction about the other agents in the environment is approximately correct and b) an agent can not correctly predict the others' behaviour. The results presented show when, where and why learning is effective when it comes to making a decision about selecting a coordination mechanism.
1106-1113
Excelente-Toledo, C. B.
3e8f210d-7ee3-4c1f-8148-6f392ad9f77b
Jennings, N. R.
ab3d94cc-247c-4545-9d1e-65873d6cdb30
2002
Excelente-Toledo, C. B.
3e8f210d-7ee3-4c1f-8148-6f392ad9f77b
Jennings, N. R.
ab3d94cc-247c-4545-9d1e-65873d6cdb30
Excelente-Toledo, C. B. and Jennings, N. R.
(2002)
Learning to select a co-ordination mechanism.
1st International Joint Conference on Autonomous Agents and Multi-Agent Systems, Bologna, Italy.
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
This paper examines the potential and the impact of introducing learning capabilities into autonomous agents that make decisions at run-time about which mechanism to exploit in order to coordinate their activities. Specifically, the efficacy of learning is evaluated for making the decisions that are involved in determining when and how to coordinate. Our motivating hypothesis is that to deal with dynamic and unpredictable environments it is important to have agents that can learn the right situations in which to attempt to coordinate and the right method to use in those situations. This hypothesis is evaluated empirically, using reinforcement based algorithms, in a grid-world scenario in which a) an agent's prediction about the other agents in the environment is approximately correct and b) an agent can not correctly predict the others' behaviour. The results presented show when, where and why learning is effective when it comes to making a decision about selecting a coordination mechanism.
Text
cora-aamas-02.pdf
- Other
More information
Published date: 2002
Venue - Dates:
1st International Joint Conference on Autonomous Agents and Multi-Agent Systems, Bologna, Italy, 2002-01-01
Organisations:
Agents, Interactions & Complexity
Identifiers
Local EPrints ID: 256870
URI: http://eprints.soton.ac.uk/id/eprint/256870
PURE UUID: d3ceeab3-5bdd-4b38-bffe-3be4d2ef0954
Catalogue record
Date deposited: 13 Jun 2003
Last modified: 14 Mar 2024 05:49
Export record
Contributors
Author:
C. B. Excelente-Toledo
Author:
N. R. Jennings
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