scholarly journals A Hybrid Three Layer Architecture for Fire Agent Management in Rescue Simulation Environment

10.5772/5796 ◽  
2005 ◽  
Vol 2 (2) ◽  
pp. 12 ◽  
Author(s):  
Alborz Geramifard ◽  
Peyman Nayeri ◽  
Reza Zamani-Nasab ◽  
Jafar Habibi
Keyword(s):  
Decision Making ◽  
Intelligent Agents ◽  
Simulation System ◽  
Hybrid Architecture ◽  
Simulation Environment ◽  
Layered Architecture ◽  
Fire Extinguishing ◽  
Three Layer Architecture ◽  
Multi Agent ◽  
Robocup Rescue

This paper presents a new architecture called FAIS for implementing intelligent agents cooperating in a special Multi Agent environment, namely the RoboCup Rescue Simulation System. This is a layered architecture which is customized for solving fire extinguishing problem. Structural decision making algorithms are combined with heuristic ones in this model, so it's a hybrid architecture.

REINFORCEMENT LEARNING FOR DECISION-MAKING IN A BUSINESS SIMULATOR

2012 ◽  
Vol 11 (05) ◽  
pp. 935-960 ◽  
Author(s):  
JAVIER GARCÍA ◽  
FERNANDO BORRAJO ◽  
FERNANDO FERNÁNDEZ
Keyword(s):  
Decision Making ◽  
Reinforcement Learning ◽  
Business Education ◽  
Intelligent Agents ◽  
Continuous Variables ◽  
Web Based ◽  
Business Decision ◽  
Decision Variables ◽  
Learning Scenarios ◽  
Multi Agent

Business simulators are powerful tools for both supporting the decision-making process of business managers as well as for business education. An example is SIMBA (SIMulator for Business Administration), a powerful simulator which is currently used as a web-based platform for business education in different institutions. In this paper, we propose the application of reinforcement learning (RL) for the creation of intelligent agents that can manage virtual companies in SIMBA. This application is not trivial, given the particular intrinsic characteristics of SIMBA: it is a generalized domain where hundreds of parameters modify the domain behavior; it is a multi-agent domain where both cooperation and competition among different agents can coexist; it is required to set dozens of continuous decision variables for a given business decision, which is made only after the study of hundreds of continuous variables. We will demonstrate empirically that all these challenges can be overcome through the use of RL, showing results for different learning scenarios.

scholarly journals ALGORITHMS FOR FINDING OPTIMAL POLICY FOR INTELLIGENT AGENTS BASED ON MARKOV DECISION-MAKING PROCESSES

2018 ◽  
pp. 29-32
Author(s):  
A. V. Lachikhin
Keyword(s):  
Decision Making ◽  
Dynamic Programming ◽  
Optimal Policy ◽  
Intelligent Agents ◽  
Dynamic Programming Method ◽  
Multi Agent Systems ◽  
Markov Decision ◽  
Decision Making Processes ◽  
Multi Agent ◽  
Method Of Dynamic Programming

Currently, the paradigm of intelligent agents and multi-agent systems is actively developing. The policy of agents ‘ actions can be represented as a Markov decision-making process. Such agents need methods to develop optimal policies. The purpose of this study is to review existing techniques, determine the possibility and conditions of their application. The main approaches based on linear and dynamic programming are considered. The specific algorithms used to find the extreme value of utility are given. The method of linear programming - simplex method, and the method of dynamic programming method-iteration of values are considered. The equations necessary to find the optimal policy of intelligent agent actions are given. Restrictions of application of various algorithms are considered. Conclusions the most suitable method for finding the optimal policy is the iteration of values.

The use of intelligent agents in modeling an integrated information system of transport logistics

2020 ◽  
Vol 5 ◽  
pp. 59-66
Author(s):  
Y.M. Iskanderov ◽  
Keyword(s):  
Information System ◽  
Supply Chains ◽  
Intelligent Agents ◽  
Technological Processes ◽  
Transport Services ◽  
Wide Range ◽  
Integrated Information System ◽  
Multi Agent ◽  
Transport Logistics ◽  
Integrated Information

Aim. The use of intelligent agents in modeling an integrated information system of transport logistics makes it possible to achieve a qualitatively new level of design of control systems in supply chains. Materials and methods. The article presents an original approach that implements the possibilities of using multi-agent technologies in the interests of modeling the processes of functioning of an integrated information system of transport logistics. It is shown that the multi-agent infrastructure is actually a semantic shell of the information system, refl ecting the rules of doing business and the interaction of its participants in the supply chains. The characteristic of the model of the class of an intelligent agent, which is basic for solving problems of management of transport and technological processes, is given. Results. The procedures of functioning of the model of integration of information resources of the participants of the transport services market on the basis of intelligent agents are considered. The presented procedures provide a wide range of network interaction operations in supply chains, including traffi c and network structure “fl exible” control, mutual exchange of content and service information, as well as their distributed processing, and information security. Conclusions. The proposed approach showed that the use of intelligent agents in modeling the functioning of an integrated information system makes it possible to take into account the peculiarities of transport and technological processes in supply chains, such as the integration of heterogeneous enterprises, their distributed organization, an open dynamic structure, standardization of products, interfaces and protocols.

scholarly journals Spending Political Capital*

2021 ◽  
Author(s):  
Arthur Campbell
Keyword(s):  
Decision Making ◽  
Incentive Contracts ◽  
Important Task ◽  
Political Capital ◽  
Alternative Mechanism ◽  
Team Size ◽  
Current Period ◽  
Multi Agent ◽  
Participation In Decision Making ◽  
Number Of Individuals

Abstract An important task for organizations is establishing truthful communication between parties with differing interests. This task is made particularly challenging when the accuracy of the information is poorly observed or not at all. In these settings, incentive contracts based on the accuracy of information will not be very effective. This paper considers an alternative mechanism that does not require any signal of the accuracy of any information communicated to provide incentives for truthful communication. Rather, an expert sacrifices future participation in decision-making to influence the current period’s decision in favour of their preferred project. This mechanism captures a notion often described as ‘political capital’ whereby an individual is able to achieve their own preferred decision in the current period at the expense of being able to exert influence in future decisions (‘spending political capital’). When the first-best is not possible in this setting, I show that experts hold more influence than under the first-best and that, in a multi-agent extension, a finite team size is optimal. Together these results suggest that a small number of individuals hold excessive influence in organizations.

scholarly journals A Confrontation Decision-Making Method with Deep Reinforcement Learning and Knowledge Transfer for Multi-Agent System

Symmetry ◽  
2020 ◽  
Vol 12 (4) ◽  
pp. 631
Author(s):  
Chunyang Hu
Keyword(s):  
Decision Making ◽  
Reinforcement Learning ◽  
Knowledge Transfer ◽  
Large Scale ◽  
Effective Control ◽  
Small Scale ◽  
Learning Agent ◽  
Multi Agent ◽  
Transfer Method ◽  
Parameter Sharing

In this paper, deep reinforcement learning (DRL) and knowledge transfer are used to achieve the effective control of the learning agent for the confrontation in the multi-agent systems. Firstly, a multi-agent Deep Deterministic Policy Gradient (DDPG) algorithm with parameter sharing is proposed to achieve confrontation decision-making of multi-agent. In the process of training, the information of other agents is introduced to the critic network to improve the strategy of confrontation. The parameter sharing mechanism can reduce the loss of experience storage. In the DDPG algorithm, we use four neural networks to generate real-time action and Q-value function respectively and use a momentum mechanism to optimize the training process to accelerate the convergence rate for the neural network. Secondly, this paper introduces an auxiliary controller using a policy-based reinforcement learning (RL) method to achieve the assistant decision-making for the game agent. In addition, an effective reward function is used to help agents balance losses of enemies and our side. Furthermore, this paper also uses the knowledge transfer method to extend the learning model to more complex scenes and improve the generalization of the proposed confrontation model. Two confrontation decision-making experiments are designed to verify the effectiveness of the proposed method. In a small-scale task scenario, the trained agent can successfully learn to fight with the competitors and achieve a good winning rate. For large-scale confrontation scenarios, the knowledge transfer method can gradually improve the decision-making level of the learning agent.

Sign in / Sign up

Export Citation Format

Share Document