Using reinforcement learning to coordinate better
Using reinforcement learning to coordinate better
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, our motivating hypothesis is that to deal with dynamic and unpredictable environments it is important to have agents that learn the right situations in which to attempt coordination and the right coordination method to use in those situations. In particular, the efficacy of learning is evaluated when agents have varying types and amounts of information when those coordinating decisions are taken. This hypothesis is evaluated empirically, in a grid-world scenario in which a) an agent’s predictions about the other agents in the environment are approximately correct and b) an agent cannot 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.
Coordination, agent interaction, collaborative agents, reinforcement learning
217-245
Excelente-Toledo, C.B.
20ddd7e4-1e7d-4b11-9ce2-fa8bd6676984
Jennings, N. R.
ab3d94cc-247c-4545-9d1e-65873d6cdb30
2005
Excelente-Toledo, C.B.
20ddd7e4-1e7d-4b11-9ce2-fa8bd6676984
Jennings, N. R.
ab3d94cc-247c-4545-9d1e-65873d6cdb30
Excelente-Toledo, C.B. and Jennings, N. R.
(2005)
Using reinforcement learning to coordinate better.
Computational Intelligence, 21 (3), .
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, our motivating hypothesis is that to deal with dynamic and unpredictable environments it is important to have agents that learn the right situations in which to attempt coordination and the right coordination method to use in those situations. In particular, the efficacy of learning is evaluated when agents have varying types and amounts of information when those coordinating decisions are taken. This hypothesis is evaluated empirically, in a grid-world scenario in which a) an agent’s predictions about the other agents in the environment are approximately correct and b) an agent cannot 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
CI05.pdf
- Accepted Manuscript
Text
j.1467-8640.2005.00272.x.pdf
- Version of Record
More information
Published date: 2005
Keywords:
Coordination, agent interaction, collaborative agents, reinforcement learning
Organisations:
Agents, Interactions & Complexity
Identifiers
Local EPrints ID: 260811
URI: http://eprints.soton.ac.uk/id/eprint/260811
PURE UUID: 77b53b10-0c27-42a4-a112-f6d4b67493f5
Catalogue record
Date deposited: 29 Apr 2005
Last modified: 14 Mar 2024 06:43
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