Multi-agent Polygon Formation using Reinforcement Learning

B. K. Swathi Prasad, Aditya G. Manjunath, Hariharan Ramasangu

2017

Abstract

This work provides details a simulation experiment and analysis of Q-learning applied to multi-agent systems. Six agents interact within the environment to form hexagon, square and triangle, by reaching their specific goal states. In the proposed approach, the agents form a hexagon and the maximum dimension of this pattern is be reduced to form patterns with smaller dimensions. A decentralised approach of controlling the agents via Q-Learning was adopted which reduced complexity. The agents will be able to either move forward, backward and sideways based on the decision taken. Finally, the Q-Learning action-reward system was designed such that the agents could exploit the system which meant that they would earn high rewards for correct actions and negative rewards so the opposite.

Paper Citation

in Harvard Style

Prasad B., Manjunath A. and Ramasangu H. (2017). Multi-agent Polygon Formation using Reinforcement Learning . In Proceedings of the 9th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-758-219-6, pages 159-165. DOI: 10.5220/0006187001590165

in Bibtex Style

@conference{icaart17,
author={B. K. Swathi Prasad and Aditya G. Manjunath and Hariharan Ramasangu},
title={Multi-agent Polygon Formation using Reinforcement Learning},
booktitle={Proceedings of the 9th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2017},
pages={159-165},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006187001590165},
isbn={978-989-758-219-6},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - Multi-agent Polygon Formation using Reinforcement Learning
SN - 978-989-758-219-6
AU - Prasad B.
AU - Manjunath A.
AU - Ramasangu H.
PY - 2017
SP - 159
EP - 165
DO - 10.5220/0006187001590165