Iranian Conference on Intelligent Systems (ICIS) , 2014-02-04

Title : ( Dynamic Agent-Based Reward Shaping for Multi-Agent Systems )

Authors: Mohammad Reza Akbarzadeh Totonchi , مریم صادقلو , Mohammad Bagher Naghibi Sistani ,

Access to full-text not allowed by authors

Citation: BibTeX | EndNote

Abstract

Earlier works have reported that reward shaping accelerates the convergence of reinforcement learning algorithms. It also helps to make better use of existing information. In this article we propose the use to modify Qlearning in multi agent systems by the use of reward shaping depending on agent state regarding other agents. We study this method with different choices, which indicate different effects of this method on the maze problem. The results indicate the directional search, reduces the number of steps to reach the target in the proposed modified approach if appropriate parameters are utilized

Keywords

, Keywords, multi, agent systems;reward shaping;agentbased learning
برای دانلود از شناسه و رمز عبور پرتال پویا استفاده کنید.

@inproceedings{paperid:1043589,
author = {Akbarzadeh Totonchi, Mohammad Reza and مریم صادقلو and Naghibi Sistani, Mohammad Bagher},
title = {Dynamic Agent-Based Reward Shaping for Multi-Agent Systems},
booktitle = {Iranian Conference on Intelligent Systems (ICIS)},
year = {2014},
location = {بم, IRAN},
keywords = {Keywords-multi-agent systems;reward shaping;agentbased learning},
}

[Download]

%0 Conference Proceedings
%T Dynamic Agent-Based Reward Shaping for Multi-Agent Systems
%A Akbarzadeh Totonchi, Mohammad Reza
%A مریم صادقلو
%A Naghibi Sistani, Mohammad Bagher
%J Iranian Conference on Intelligent Systems (ICIS)
%D 2014

[Download]