arrow
返回

Knowledge-Based Multiagent Credit Assignment: A Study on Task Type and Critic Information

delete2007-09-01
delete18
PRE
AI
A
Ahad Harati *
M
Majid Nili Ahmadabadi
B
Babak Nadjar Araabi
DOI:10.1109/JSYST.2007.901641delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Multiagent credit assignment (MCA) is one of the major problems in the realization of multiagent reinforcement learning. Since the environment usually is not intelligent enough to qualify individual agents in a cooperative team, it is very important to develop some methods for assigning individual agents' credits when just a single team reinforcement is available. MCA cannot be solved in general cases, using a single technique. Therefore, our goal in this research is first to present a new view of the problem and second, to introduce a new idea of using agents' knowledge to partially solve MCA. In this research, an approach that is based on agents' learning histories and knowledge is proposed to solve the MCA problem. Knowledge evaluation-based credit assignment (KEBCA) along with certainty, a measure of agents' knowledge, is developed to judge agents' actions and to assign them proper credits. The proposed KEBCA method is general, however; we study it in some simulated extreme cases in order to gain a better insight into MCA problem and to evaluate our approach in such cases. More specifically, we study the effects of task type (AND-type and OR-type tasks) on solving MCA problem in two cases. In the first case, in addition to the team reinforcement, it is assumed that some extra information at the team level is available. In the second case, such extra information does not exist. In addition, performance of the system is examined in presence of some uncertainties in the environment, modeled as noise on agents' actions. The information content of team reinforcements and assumed extra information are theoretically calculated and discussed. The mathematical calculations confirm the related simulation results.
Keyword:
Credit assignment
multiagent learning
reinforcement learning

期刊

I
IEEE Open Journal of Circuits and Systems
IF:
2.4
论文数:
4.5K
被引数:
387

机构

U
University of Tehran
学者数:
2.4W
论文数: 2.3W
被引数: 2.7W
引用论文

引用论文

A CURIOUS CASE OF MERCURY-INDUCED MEMBRANOUS NEPHROPATHY一例罕见的汞诱导性膜性肾病病例
err2025-04-01
err0
PREAI
errMcconnell, Ramsay; Khan, Kazi; Nayer, Hassan; Shumburo, Khalid; Choi, Michael
err分享
err收藏
err分享
err收藏
err分享
err收藏
err分享
err收藏
学者 查看更多内容