scholarly journals SYSTEM ANALYSIS IN HIERARCHICAL INTELLIGENT MULTI-AGENT SYSTEMS

2021 ◽  
pp. 33-46
Author(s):  
V. S. Simankov ◽  
Yu. V. Dubenko
Keyword(s):  
Reinforcement Learning ◽  
System Analysis ◽  
Three Dimensional ◽  
Label Propagation ◽  
Multi Agent System ◽  
Multi Agent Systems ◽  
Agent Systems ◽  
Hierarchical Reinforcement Learning ◽  
Multi Agent ◽  
Weight Coefficients

The system analysis of the hierarchical intelligent multi-agent system in general, as well as its main structural unit, the intelligent agent, its major subsystems identified. As part of the analysis of the computer vision subsystem, it was concluded that the considered sources have insufficiently worked out issues related to the processing of occlusions, with the automation of the process of reconstruction of three-dimensional scenes, with the implementation of the processing of an unstructured set of images. The structure of the block for the reconstruction of three-dimensional scenes is proposed, the implementation of which is aimed at eliminating the indicated problems characteristic of the machine vision subsystem. The analysis of the main methods of implementing unsupervised learning is carried out, based on the results of which it is concluded that it is advisable to use reinforcement learning when implementing systems of this type. Such types of reinforcement learning as hierarchical reinforcement learning and multi-agent reinforcement learning are considered. A method for segmentation of macro actions is proposed, based on the implementation of clustering by the method of label propagation, in which the number of transitions is formalized in the form of weight coefficients of edges.

The Effect of Reward Interdependence of Strategies in Evolutionary Multi-Agent Systems

2009 ◽  
Author(s):  
Lindsay Hanna ◽  
Jonathan Cagan
Keyword(s):  
Organizational Behavior ◽  
System Analysis ◽  
Three Dimensional ◽  
Computational Design ◽  
Design Teams ◽  
Multi Agent Systems ◽  
Agent Systems ◽  
Effective Strategies ◽  
Multi Agent ◽  
Potential Impact

This paper explores the effect of reward interdependence of strategies in a cooperative evolving team on the performance of the team. Experiments extending the Evolutionary Multi-Agent Systems (EMAS) framework to three dimensional layout are designed which examine the effect of rewarding helpful, in addition to effective strategies on the convergence of the system. Analysis of communication within the system suggests that some agents (strategies) are more effective at creating helpful solutions than creating good solutions. Despite their potential impact as enablers for other strategies, when their efforts were not rewarded, these assistant agent types were quickly removed from the population. When reward was interdependent, however, this secondary group of helpful agents remained in the population longer. As a result, effective communication channels remained open and the system converged more quickly. The results support conclusions of organizational behavior experimentation and computational modeling. The implications of this study are twofold. First, computational design teams may be made more effective by recognizing and rewarding indirect contributions of some strategies to the success of others. Secondly, EMAS may provide a platform for predicting the effectiveness of different reward structures given a set of strategies in both human and computational teams.

scholarly journals GENERAL MODEL FOR ORGANIZING INTERACTIONS IN MULTI-AGENT SYSTEMS

2014 ◽  
pp. 224-233
Author(s):  
Anton Kabysh ◽  
Vladimir Golovko
Keyword(s):  
Reinforcement Learning ◽  
General Model ◽  
Payoff Function ◽  
Multi Agent System ◽  
Multi Agent Systems ◽  
Learning Paradigm ◽  
Agent Systems ◽  
Multi Agent ◽  
Value Learning

In this article we describe a model for finding optimal for learning the behavior of a group of agents in a collaborative multiagent setting. This model contains a set of scalable techniques that organize behavior of a multi- agent system. As a basis we use the framework of coordination graphs which exploits the dependencies between agents to decompose the global payoff function into a sum of local terms. To estimate a quality of interactions between agents we are using the concepts of the influence value learning paradigm. In last section we present the implementation of the considered model via reinforcement learning and experimental results of the use of this paradigm.

Improvement on Supporting Machine Learning Algorithm for Solving Problem in Immediate Decision Making

2012 ◽  
Vol 566 ◽  
pp. 572-579
Author(s):  
Abdolkarim Niazi ◽  
Norizah Redzuan ◽  
Raja Ishak Raja Hamzah ◽  
Sara Esfandiari
Keyword(s):  
Reinforcement Learning ◽  
Learning Algorithm ◽  
Multi Agent Systems ◽  
Combined Model ◽  
Q Learning ◽  
Agent Systems ◽  
Multi Agent ◽  
Case Base ◽  
Case Base Reasoning ◽  
Robotic Tool

In this paper, a new algorithm based on case base reasoning and reinforcement learning (RL) is proposed to increase the convergence rate of the reinforcement learning algorithms. RL algorithms are very useful for solving wide variety decision problems when their models are not available and they must make decision correctly in every state of system, such as multi agent systems, artificial control systems, robotic, tool condition monitoring and etc. In the propose method, we investigate how making improved action selection in reinforcement learning (RL) algorithm. In the proposed method, the new combined model using case base reasoning systems and a new optimized function is proposed to select the action, which led to an increase in algorithms based on Q-learning. The algorithm mentioned was used for solving the problem of cooperative Markov’s games as one of the models of Markov based multi-agent systems. The results of experiments Indicated that the proposed algorithms perform better than the existing algorithms in terms of speed and accuracy of reaching the optimal policy.

Sign in / Sign up

Export Citation Format

Share Document