Loading...
Search for: multiagent-systems
0.01 seconds
Total 52 records

    A Study on Credit Assignment among Reinforcement Learning Agents

    , M.Sc. Thesis Sharif University of Technology Rahaie, Zahra (Author) ; Beigy, Hamid (Supervisor)
    Abstract
    Nowadays, multi-agent systems as part of the distributed artificial intelligence play an important role in modeling and solving complex industrial and commercial problems. They have distinguishing characteristics such as distributiveness (spatial, temporal, semantic, or functional distribution), robustness, parallel processing, etc. One of the capabilities that can be added to this system is the learning capability. It can help the system to adapt itself to the new environment. This paper proposed a method for the problem of credit assignment in multi-agent domain. Solving the multi-agent credit assignment problem, one can expect individual learning for a single agent in systems of... 

    Evaluation of NeuroEvolution of Augmenting Topologies in Cooperative Multi-Agent Learning

    , M.Sc. Thesis Sharif University of Technology Iravanian, Sina (Author) ; Mahdavi Amiri, Nezameddin (Supervisor) ; Beigy, Hamid (Supervisor)
    Abstract
    In multi-agent systems (MAS), collective behavior of autonomous agents and complexities arisen by their interactions are studied, while they are exploited to solve real-world complex problems. Machine learning methods are frequently used for problem solving in MAS, because complexities in these systems prevent a programmer to thoroughly describe the agents’ behaviors and the rules governing them.Reinforcement learning (RL) is one of the most commonly used learning methods for intelligent agents,because it does not need a model of the environment and learns agents’ policies through trial and error.Conventional RL algorithms store and update utilities for every possible state in a table. One... 

    A distributed algorithm for managing residential demand response in smart grids

    , Article IEEE Transactions on Industrial Informatics ; Vol. 10, issue 4 , November , 2014 , p. 2385-2393 ; ISSN: 15513203 Safdarian, A ; Fotuhi-Firuzabad, M ; Lehtonen, M ; Sharif University of Technology
    Abstract
    Demand response enabled by time-varying prices can propel the power industry toward a greater efficiency. However, a noncoordinated response of customers may lead to severe peak rebounds at periods with lower prices. In this regard, a coordinated demand response scheme can mitigate concerns about the peak rebounds. This paper presents a system-wide demand response management model to coordinate demand response provided by residential customers. The objective of the model is to flatten the total load profile that is subject to minimum individual cost of customers. The model is first formulated as a bi-level optimization problem. It is then casted into equivalent single-level problems, which... 

    RoboCupRescue system and arian: A flexible infrastructure for multi-agent research and education

    , Article Proceedings: 15th IEEE International Conference on Tools with artificial Intelligence, Sacramento, CA, 3 November 2003 through 5 November 2003 ; 2003 , Pages 351-355 ; 10636730 (ISSN) Ahmadi, M ; Takahashi, T ; Habibi, J ; Koto, T ; IEEE Computer Society ; Sharif University of Technology
    2003
    Abstract
    One of the main requisites for multi agent researchers is a multi-purpose infrastructure that enables them to create, test and evaluate protocols, methods and algorithms. RoboCupRescue simulation environment is a flexible and configurable environment that can fill this gap. With changes in its configuration files, it will gain different features, so different methods can be designed, implemented, and tested. This environment is actually suitable for most multi-agent research issues such as cooperation, coordination, agent communication languages, and agent micro level issues. Sensible roles and tasks in the system motivate more research and make this environment a suitable infrastructure for... 

    Decentralized and Scalable Control of Multi-Agent Systems for Obstacle Avoidance and Changing Formation

    , M.Sc. Thesis Sharif University of Technology Firooze, Vahid (Author) ; Sayyaadi, Hassan (Supervisor)
    Abstract
    Coordinate motion is a considerable phenomenon in biology and very powerful tool for leading and controlling a group of robots. In recent years, robotic becomes a helpful technology for acompilishing in works which is impossiple for human, such as working in toxic environments. In this project, we introduce coordinate motion problems which are applicable in multi-agent systems, and we also present suitable control algorithms for solving this problem. In other word, we use potential field method to model coordinate motion. We propose a three-cycle robot as an agent, such that it has two nonholonomic constraints. Designing an algorithm for solving coordinate motion problems, we propose these... 

    Modeling and Simulation of the Behavior of Cancer Cells, A Multi-agent Approach

    , M.Sc. Thesis Sharif University of Technology Fazli, Rasol (Author) ; Habibi, Jafar (Supervisor)
    Abstract
    Cancer is a complicated disease. So, cancer treatment can not be possible without understanding its complex behavior. Each of cells do inner operations spontaneously and have interactions on external environment. This feature of cells has caused to model their behaviors using multi-agents and considering each cell as an intelligent agent. Using this approach, a novel multi-scale agent-based model known as basic model has been introduced. Furthermore, two signaling pathways have been added to this model. For simulation, a new agent-based modeling framework has been proposed. After that, learning has been involved, for considering drug effects. Finally, by means of this model we can predict... 

    Water Allocation Modelling on the Basis of Hydrological Characteristics Critical Plains (Case Study: Mashhad Plain)

    , M.Sc. Thesis Sharif University of Technology (Author) ; Agha Mohammad Hossein Tajrishi, Massoud (Supervisor)
    Abstract
    The Mashhad plain is one of the most important plains in Khorasan-e-Razavi province. In the last decades, rapid population growth coupled with agricultural expansion has tremendously increases pressure on the groundwater resources. Large increases in water demands with little recharge have strained the plain groundwater resources resulting in declines in water level in last decades. Due to declining of groundwater level, digging new wells has been forbidden since 1965. In this thesis, users in agricultural, municipals and industrial sections have been modeled with Multi-Agent System, and results of their water extraction on groundwater level have been modeled with GMS. There are two... 

    Multi-agent based Blockchain Simulation Framework

    , M.Sc. Thesis Sharif University of Technology Alimirzaei, Fatemeh (Author) ; Tefagh, Mojtaba (Supervisor)
    Abstract
    A multi-agent system is a system consisting of several intelligent agents. In fact, a multi-agent system is a system that includes a large number of agents that communicate with each other through message transmission in a network structure. Multi-agent systems can solve problems that are difficult or impossible for a single agent or an integrated system to solve. Blockchain is an example of these multi-agent systems that has many use cases in different fields for example cryptocurrencies . A blockchain is a growing ledger consisting of records called blocks. In this thesis, we want to provide tools for the simulation of this multi-agent system so that we can model the issues surrounding... 

    Optimization on Initial Position and Number of Informed Agents in a Flocking in Presence of Obstacles

    , M.Sc. Thesis Sharif University of Technology Paygani, Alireza (Author) ; Haeri, Mohammad (Supervisor)
    Abstract
    dFlocking in multi-agent systems as one of the most interested phenomena has gained scientists and researchers attention in recent years. In a multi-agent system, agents by using a consensus algorithm, which designed based on collective, collision avoidance, and velocity adaption rules, try to catch a common goal together. The aims which may define for flocking of a multi-agent system include the getting a certain point, chasing an alien agent, moving in a given route, and so on. Without considering flock’s purposes, all agents must be aware about the goal to catch it. But it is not possible always to inform all agents about the goal. Because sending the goal information to all agents due to... 

    Target Tracking Using Multi-Agent Systems With Inertial and Non-Holonomic Agents

    , M.Sc. Thesis Sharif University of Technology Roshanghalb, Farhad (Author) ; Sayyaadi, Hassan (Supervisor)
    Abstract
    Behavioral investigation and control of multi-agent systems was one of the most attractive problems in robotics which has been studied since the middle of 20th century. Tracking a target is shown by many organic mechanisms during hunting and etc. and is one of the important topics of researches. In this thesis tracking a target by a multi-agent system has been considered which the agents are wheeled mobile robots and have non-holonomic motion constraints. A sample dimensionless and continuous time synchronous dynamic is proposed for the motion of these agents and the goal is to track a moving target while the agents create and keep a desired formation during their tracking process.... 

    Dynamics and Control of a Set of Wheeled Robots on a Non-planar Surfaces to Perform Specific Mission

    , M.Sc. Thesis Sharif University of Technology Sabet, Mohammad Taghi (Author) ; Sayyaadi, Hassan (Supervisor)
    Abstract
    The aim of this article is ancestral control of a set of 3-wheel robots with non-holonomics dynamics for hunting and covering around moving target. Robots have mass and inertia and the wheels' mass have been considered in the dynamics of robots. The output of controller is wheel's torque and front wheel's steering torque. Moving target dynamics has been considered in a way that it is escaping from invader and the target has holonomics dynamic. To derive the equation of motion, Kane's dynamics procedure has been used. Robots are equipped to sensors for distance assessment, vision angle assessment and also signal receiver antenna. To estimate relative position and variables of other robots'... 

    A Framework for Engineering Agent-oriented Methodologies

    , M.Sc. Thesis Sharif University of Technology Azadbakht, Keyvan (Author) ; Ramsin, Raman (Supervisor)
    Abstract
    Agents are autonomous entities that have independent threads of control, and that interact with each other in their environment. Due to the intelligence of agents and their ability as to social interaction, an agent-oriented system exhibits remarkable synergistic traits. Agent-oriented software development facilitates the development of flexible systems that exhibit complex behaviors.Traditional software development methodologies do not sufficiently satisfy the special needs of the agent-oriented paradigm. Therefore, many researchers have focused on developing specialized agent-oriented methodologies, or have worked on extending or adapting existing methodologies so that they can be used for... 

    Multi Agent System Approach to Sustainability Analysis of Airline Alliances

    , M.Sc. Thesis Sharif University of Technology Mohammad Salehi, Saeed (Author) ; Malaek, Mohammad Bagher (Supervisor)
    Abstract
    Today global network of transportation is mainstream for economic growth and business development, growth in population made a need in optimization of using routes in global air transportation network, research shows cooperating with Airline Alliances is beneficial and gives much more freedom to their members in schedule planning and pricing as well as common interest in market share in international market. Joining an alliance affects decision making process of airline (e.g. fleet design, scheduling, route planning and crew assignment) in competitive market. Difficulty and complexity of evaluation in cooperative decision making that needs research to develop a model to evaluate decision... 

    Feasibility Study of Offering Generalized Equivalent Model for Drag Polar in Formation Flight

    , M.Sc. Thesis Sharif University of Technology Behnam Nia, Fahimeh (Author) ; Malaek, Mohammad Bagher (Supervisor)
    Abstract
    The increasing demand for air transportation, along with air traffic limitations and environmental pollution concerns, necessitate a comprehensive study in the field of airspace-management. In this regard, one of the promising alternatives is flying smarter via “Formations”. In fact, many works have discussed the benefits of “Commercial Formation Flights”; however, none have discussed a practical way to manage such formations for long-distance cruise. This paper discusses a new approach to manage the “Geometrical Arrangement” of such flights in an efficient manner. In fact, with the help of the so called “Game Theory” and without complex computations we are able to guide each individual... 

    Design and Construction of Two-Wheeled Mobile Robot Platform with the Ability to Connect to other Robots with Two Rotational Degrees of Freedom

    , M.Sc. Thesis Sharif University of Technology Golmirzaei, Ali (Author) ; Sayyaadi, Hassan (Supervisor)
    Abstract
    Due to the advantages of multi-agent systems, research in this area and the use of these systems in industry are increasingly growing. Applying these robots, various complex tasks can be done faster, safer and with better results. In our country, many different algorithms have been proposed and simulated, but due to the lack of a real environment for implementation, their actual performance has not been assessed. This project aims to create a platform for research and development of this field. This goal is achieved by performing the first phase of implementation, namely the design and construction of the robot platform. In the first step, qualitative and quantitative characteristics of the... 

    Cooperation Control of a Set of Robots with Different Expertise to Accomplish a Duty

    , M.Sc. Thesis Sharif University of Technology Mortazi, Ali Asghar (Author) ; Bagheri Shouraki, Saeed (Supervisor)
    Abstract
    In recent years, there have been many efforts for distributing a big and complex duty among some agents in order to do it more simply. Large number of these methods are in area called distributed systems, where several different agents start to work together to do a difficult or complex duty which each of them cannot do it lonely. Combination of distributed systems and artificial intelligence is known as distributed artificial intelligence.
    One of the theories that has received attention recently, is called Embodiment. According this theory, in cooperation of a set of agents for performing particular task, expertise might not be integrated in a centralized controller, rather it gradually... 

    A Game Theory Approach to Airline Fleet Desing; a Case of Commercial Formation Flight

    , M.Sc. Thesis Sharif University of Technology Lourak Agha, Hamid Reza (Author) ; Malaek, Mohammad Bagher (Supervisor)
    Abstract
    Increasing aviation share in air pollution, population growth, scarcity of available resources such as land (airport), airspace and energy along with uncertainties in air transportation demand and energy market, has motivated the industry stakeholders to push researches toward sustainable models in fleet planning and design. In this thesis we have investigated the suitability of a decision-making model for airline fleet management, based on “Game Theory” and the idea of commercial formation flight (COFOFS). We intend to examine the circumstances under which, an airline needs to substitute a wide-body aircraft with number of smaller ones, while employing the approach of formation flight.... 

    Design Patterns for Agent-Oriented Software Engineering, and Formalizing Design Patterns

    , M.Sc. Thesis Sharif University of Technology Rahmani, Hazhar (Author) ; Ramezanian, Rasoul (Supervisor)
    Abstract
    Agent-Oriented Software Engineering is one of the novel and growing paradigms in computer science, which provides systematic approaches for analysis, designing, implementation and maintenance of multi-agent systems. Agents are the main entities of the agent-oriented software systems. Agents are autonomous and behave flexibly and intelligently. This paradigm is appropriate for developing open, complex, flexible and distributed systems. Design pattern is a general reusable solution to a commonly occurring problem within a specific context in software design. Using patterns in software design has many benefits such as increasing the quality and robustness of the software. Regarding the fact... 

    An Agent-Based Approach to Forming Logic of Commercial Formation Flights

    , M.Sc. Thesis Sharif University of Technology Baleghi, Behzad (Author) ; Malaek, Mohammad Bagher (Supervisor)
    Abstract
    The existing trend in air transportation growth, clearly shows that aviation industries need to profoundly look at “formation flights” in a more efficient manner and without complex computations. This work describes a new efficient Logic to accept or reject a possible formation among all available. The approach considers each airplane as an agents that “sees” the current traffic environment and then selects the best “Action” to satisfy its desired objectives. The logic, although simple, considers the location and time to join a formation or to create one; and the position to leave the original formation. Different Mathematical model have been investigated to find-out which one is more... 

    Control Strategies of Swarm Vessels for Circling Mission in Calm Water

    , M.Sc. Thesis Sharif University of Technology Ghasemzade Ahrami, Abbas (Author) ; Sayyadi, Hassan (Supervisor)
    Abstract
    Control of a group of autonomous surface vessels with realistic dynamic for circling mission is distributed with the aid of Lyaponov and graph theory. in this brief, to obtain a cooperative controller, new coordination transfer are presented and graph theory is used to illustrate the communication between the agents. With the aid of Lyaponov theory and graph application, Decentralized and scalable controllers are designed for group of autonomous vessels to converge to desired geometry to circling a specific target. Because of the realistic dynamics, Non-Holonmic dynamics and turning constrains of the vessels are considered in the design process. The advantage of proposed controller is: it...