Hierarchical Multi Agent Reinforcement Learning
Full Text: jaamas06.pdf
Hierarchical reinforcement learning methods have previously been shown to speed up learning primarily in single-agent domains. In this paper we explore the use of this spatio-temporal abstraction mechanism to speed up a complex multi-agent reinforcement learning task. The focus here is on domains requiring multiple agents to co-operatively learn tasks which require coordination among the agents. We adopt the MAXQ framework of hierarchical learning as it naturally extends to the multi agent.
Citation
M. Ghavamzadeh, S. Mahadevan, R. Makar. "Hierarchical Multi Agent Reinforcement Learning". Journal of Autonomous Agents and Multi-Agent Systems, June 2007.| Keywords: | machine learning |
| Category: | In Journal |
BibTeX
@article{Ghavamzadeh+al:07,
author = {Mohammad Ghavamzadeh and Sridhar Mahadevan and Rajbala Makar},
title = {Hierarchical Multi Agent Reinforcement Learning},
journal = {Journal of Autonomous Agents and Multi-Agent Systems},
year = 2007,
}Last Updated: June 08, 2007Submitted by Staurt H. Johnson
