A study on hierarchical modular reinforcement learning for multi-agent pursuit problem based on relative coordinate states

Authors:
Tatsuya Wada;Takuya Okawa;Toshihiko Watanabe
Affiliations:
Graduate School of Engineering, Osaka Electro-Communication University, Neyagawa, Osaka, Japan;Graduate School of Engineering, Osaka Electro-Communication University, Neyagawa, Osaka, Japan;Faculty of Engineering, Osaka Electro-Communication University, Neyagawa, Osaka, Japan
Venue:
CIRA'09 Proceedings of the 8th IEEE international conference on Computational intelligence in robotics and automation
Year:
2009

Citing 6
Cited 0

Technical Note: \cal Q-Learning

Machine Learning
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Credit Assignment in Rule Discovery Systems Based on Genetic Algorithms

Machine Learning
Acquisition of Stand-up Behavior by a Real Robot using Hierarchical Reinforcement Learning

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Robotic mapping: a survey

Exploring artificial intelligence in the new millennium
Q-Learning with Adaptive State Segmentation (QLASS)

CIRA '97 Proceedings of the 1997 IEEE International Symposium on Computational Intelligence in Robotics and Automation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In order to realize intelligent agent such as autonomous mobile robots, Reinforcement Learning is one of the necessary techniques in behavior control system. However, applying the reinforcement learning to actual sized problem, the "curse of dimensionality" problem in partition of sensory states should be avoided maintaining computational efficiency. In multi-agent reinforcement learning, the problem is emerged owing to the high dimensionality of each agent states. We apply the hierarchical modular reinforcement learning in order to deal with the dimensional problem and task decomposition. In this study, we focus on investigation of the learning performance of agent that represents the input states in relative coordinate system. We show effectiveness of proposed learning algorithm based on relative expressions with limited view through numerical experiments of the pursuit problem.