A reinforcement learning algorithm using temporal difference error in ant model

Authors:
SeungGwan Lee;TaeChoong Chung
Affiliations:
School of Computer Science and Information Engineering, Catholic University, Gyeonggi-Do, Korea;School of Electronics and Information, KyungHee University, Gyeonggi-Do, Korea
Venue:
IWANN'05 Proceedings of the 8th international conference on Artificial Neural Networks: computational Intelligence and Bioinspired Systems
Year:
2005

Citing 4
Cited 1

Efficient reinforcement learning

COLT '94 Proceedings of the seventh annual conference on Computational learning theory
A Study of Some Properties of Ant-Q

PPSN IV Proceedings of the 4th International Conference on Parallel Problem Solving from Nature
Ant colony system: a cooperative learning approach to the traveling salesman problem

IEEE Transactions on Evolutionary Computation
Ant system: optimization by a colony of cooperating agents

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

A cooperation online reinforcement learning approach in ant-q

ICONIP'06 Proceedings of the 13 international conference on Neural Information Processing - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

When agent chooses some action and does state transition in present state in reinforcement learning, it is important subject to decide how will reward for conduct that agent chooses. In this paper, we suggest multi colony interaction ant reinforcement learning model using TD-error to original Ant-Q learning. This method is a hybrid of multi colony interaction by elite strategy and reinforcement learning applying TD-error to Ant-Q. We could know through an experiment that proposed reinforcement learning method converges faster to optimal solution than original ACS and Ant-Q.