Multi-agent system

Last updated

Simple reflex agent IntelligentAgent-SimpleReflex.png
Simple reflex agent
Learning agent IntelligentAgent-Learning.svg
Learning agent

A multi-agent system (MAS or "self-organized system") is a computerized system composed of multiple interacting intelligent agents. [1] Multi-agent systems can solve problems that are difficult or impossible for an individual agent or a monolithic system to solve. [2] Intelligence may include methodic, functional, procedural approaches, algorithmic search or reinforcement learning. [3] With advancements in Large language model (LLMs), LLM-based multi-agent systems have emerged as a new area of research, enabling more sophisticated interactions and coordination among agents. [4]

Contents

Despite considerable overlap, a multi-agent system is not always the same as an agent-based model (ABM). The goal of an ABM is to search for explanatory insight into the collective behavior of agents (which do not necessarily need to be "intelligent") obeying simple rules, typically in natural systems, rather than in solving specific practical or engineering problems. The terminology of ABM tends to be used more often in the science, and MAS in engineering and technology. [5] Applications where multi-agent systems research may deliver an appropriate approach include online trading, [6] disaster response, [7] [8] target surveillance [9] and social structure modelling. [10]

Concept

Multi-agent systems consist of agents and their environment. Typically multi-agent systems research refers to software agents. However, the agents in a multi-agent system could equally well be robots, humans or human teams. A multi-agent system may contain combined human-agent teams.

Agents can be divided into types spanning simple to complex. Categories include:

Agent environments can be divided into:

Agent environments can also be organized according to properties such as accessibility (whether it is possible to gather complete information about the environment), determinism (whether an action causes a definite effect), dynamics (how many entities influence the environment in the moment), discreteness (whether the number of possible actions in the environment is finite), episodicity (whether agent actions in certain time periods influence other periods), [12] and dimensionality (whether spatial characteristics are important factors of the environment and the agent considers space in its decision making). [13] Agent actions are typically mediated via an appropriate middleware. This middleware offers a first-class design abstraction for multi-agent systems, providing means to govern resource access and agent coordination. [14]

Characteristics

The agents in a multi-agent system have several important characteristics: [15]

Self-organisation and self-direction

Multi-agent systems can manifest self-organisation as well as self-direction and other control paradigms and related complex behaviors even when the individual strategies of all their agents are simple.[ citation needed ] When agents can share knowledge using any agreed language, within the constraints of the system's communication protocol, the approach may lead to a common improvement. Example languages are Knowledge Query Manipulation Language (KQML) or Agent Communication Language (ACL).

System paradigms

Many MAS are implemented in computer simulations, stepping the system through discrete "time steps". The MAS components communicate typically using a weighted request matrix, e.g. 

 Speed-VERY_IMPORTANT: min=45 mph,   Path length-MEDIUM_IMPORTANCE: max=60 expectedMax=40,   Max-Weight-UNIMPORTANT   Contract Priority-REGULAR

and a weighted response matrix, e.g. 

 Speed-min:50 but only if weather sunny,   Path length:25 for sunny / 46 for rainy  Contract Priority-REGULAR  note – ambulance will override this priority and you'll have to wait

A challenge-response-contract scheme is common in MAS systems, where

also considering other components, evolving "contracts" and the restriction sets of the component algorithms.

Another paradigm commonly used with MAS is the "pheromone", where components leave information for other nearby components. These pheromones may evaporate/concentrate with time, that is their values may decrease (or increase).

Properties

MAS tend to find the best solution for their problems without intervention. There is high similarity here to physical phenomena, such as energy minimizing, where physical objects tend to reach the lowest energy possible within the physically constrained world. For example: many of the cars entering a metropolis in the morning will be available for leaving that same metropolis in the evening.

The systems also tend to prevent propagation of faults, self-recover and be fault tolerant, mainly due to the redundancy of components.

Research

The study of multi-agent systems is "concerned with the development and analysis of sophisticated AI problem-solving and control architectures for both single-agent and multiple-agent systems." [17] Research topics include:

Frameworks

Frameworks have emerged that implement common standards (such as the FIPA and OMG MASIF standards). [23] These frameworks e.g. JADE, save time and aid in the standardization of MAS development. [24]

Currently though, no standard is actively maintained from FIPA or OMG. Efforts for further development of software agents in industrial context are carried out in IEEE IES technical committee on Industrial Agents. [25]

With advancements in Large Language Models (LLMs) such as ChatGPT, LLM-based multi-agent frameworks, such as CAMEL, [26] [4] have emerged as a new paradigm for developing multi-agent applications.

Applications

MAS have not only been applied in academic research, but also in industry. [27] MAS are applied in the real world to graphical applications such as computer games. Agent systems have been used in films. [28] It is widely advocated for use in networking and mobile technologies, to achieve automatic and dynamic load balancing, high scalability and self-healing networks. They are being used for coordinated defence systems.

Other applications [29] include transportation, [30] logistics, [31] graphics, manufacturing, power system, [32] smartgrids, [33] and the GIS.

Also, Multi-agent Systems Artificial Intelligence (MAAI) are used for simulating societies, the purpose thereof being helpful in the fields of climate, energy, epidemiology, conflict management, child abuse, .... [34] Some organisations working on using multi-agent system models include Center for Modelling Social Systems, Centre for Research in Social Simulation, Centre for Policy Modelling, Society for Modelling and Simulation International. [34]

Vehicular traffic with controlled autonomous vehicles can be modelling as a multi-agent system involving crowd dynamics. [35] Hallerbach et al. discussed the application of agent-based approaches for the development and validation of automated driving systems via a digital twin of the vehicle-under-test and microscopic traffic simulation based on independent agents. [36] Waymo has created a multi-agent simulation environment Carcraft to test algorithms for self-driving cars. [37] [38] It simulates traffic interactions between human drivers, pedestrians and automated vehicles. People's behavior is imitated by artificial agents based on data of real human behavior.

See also

Related Research Articles

Distributed artificial intelligence (DAI) also called Decentralized Artificial Intelligence is a subfield of artificial intelligence research dedicated to the development of distributed solutions for problems. DAI is closely related to and a predecessor of the field of multi-agent systems.

<span class="mw-page-title-main">Boids</span> Artificial life program

Boids is an artificial life program, developed by Craig Reynolds in 1986, which simulates the flocking behaviour of birds, and related group motion. His paper on this topic was published in 1987 in the proceedings of the ACM SIGGRAPH conference. The name "boid" corresponds to a shortened version of "bird-oid object", which refers to a bird-like object. Reynolds' boid model is one example of a larger general concept, for which many other variations have been developed since. The closely related work of Ichiro Aoki is noteworthy because it was published in 1982 — five years before Reynolds' boids paper.

In computer science, a software agent is a computer program that acts for a user or another program in a relationship of agency.

<span class="mw-page-title-main">Swarm intelligence</span> Collective behavior of decentralized, self-organized systems

Swarm intelligence (SI) is the collective behavior of decentralized, self-organized systems, natural or artificial. The concept is employed in work on artificial intelligence. The expression was introduced by Gerardo Beni and Jing Wang in 1989, in the context of cellular robotic systems.

<span class="mw-page-title-main">Crowd simulation</span> Model of movement

Crowd simulation is the process of simulating the movement of a large number of entities or characters. It is commonly used to create virtual scenes for visual media like films and video games, and is also used in crisis training, architecture and urban planning, and evacuation simulation.

An agent-based model (ABM) is a computational model for simulating the actions and interactions of autonomous agents in order to understand the behavior of a system and what governs its outcomes. It combines elements of game theory, complex systems, emergence, computational sociology, multi-agent systems, and evolutionary programming. Monte Carlo methods are used to understand the stochasticity of these models. Particularly within ecology, ABMs are also called individual-based models (IBMs). A review of recent literature on individual-based models, agent-based models, and multiagent systems shows that ABMs are used in many scientific domains including biology, ecology and social science. Agent-based modeling is related to, but distinct from, the concept of multi-agent systems or multi-agent simulation in that the goal of ABM is to search for explanatory insight into the collective behavior of agents obeying simple rules, typically in natural systems, rather than in designing agents or solving specific practical or engineering problems.

<span class="mw-page-title-main">Swarm robotics</span> Coordination of multiple robots as a system

Swarm robotics is the study of how to design independent systems of robots without centralized control. The emerging swarming behavior of robotic swarms is created through the interactions between individual robots and the environment. This idea emerged on the field of artificial swarm intelligence, as well as the studies of insects, ants and other fields in nature, where swarm behavior occurs.

The belief–desire–intention software model (BDI) is a software model developed for programming intelligent agents. Superficially characterized by the implementation of an agent's beliefs, desires and intentions, it actually uses these concepts to solve a particular problem in agent programming. In essence, it provides a mechanism for separating the activity of selecting a plan from the execution of currently active plans. Consequently, BDI agents are able to balance the time spent on deliberating about plans and executing those plans. A third activity, creating the plans in the first place (planning), is not within the scope of the model, and is left to the system designer and programmer.

<span class="mw-page-title-main">Intelligent agent</span> Software agent which acts autonomously

In intelligence and artificial intelligence, an intelligent agent (IA) is an agent that perceives its environment, takes actions autonomously in order to achieve goals, and may improve its performance with learning or acquiring knowledge.

Ekaterini Panagiotou Sycara is a Greek computer scientist. She is an Edward Fredkin Research Professor of Robotics in the Robotics Institute, School of Computer Science at Carnegie Mellon University internationally known for her research in artificial intelligence, particularly in the fields of negotiation, autonomous agents and multi-agent systems. She directs the Advanced Agent-Robotics Technology Lab at Robotics Institute, Carnegie Mellon University. She also serves as academic advisor for PhD students at both Robotics Institute and Tepper School of Business.

<span class="mw-page-title-main">Ronald C. Arkin</span> American roboticist and roboethicist

Ronald Craig Arkin is an American roboticist and roboethicist, and a Regents' Professor in the School of Interactive Computing, College of Computing at the Georgia Institute of Technology. He is known for the motor schema technique in robot navigation and for his book Behavior-Based Robotics.

Agent-based social simulation consists of social simulations that are based on agent-based modeling, and implemented using artificial agent technologies. Agent-based social simulation is a scientific discipline concerned with simulation of social phenomena, using computer-based multiagent models. In these simulations, persons or group of persons are represented by agents. MABSS is a combination of social science, multiagent simulation and computer simulation.

Agent-oriented programming (AOP) is a programming paradigm where the construction of the software is centered on the concept of software agents. In contrast to object-oriented programming which has objects at its core, AOP has externally specified agents at its core. They can be thought of as abstractions of objects. Exchanged messages are interpreted by receiving "agents", in a way specific to its class of agents.

<span class="mw-page-title-main">Juan Pavón</span> Spanish computer scientist (b.1962)

Juan Pavón is a Spanish computer scientist, full professor of the Complutense University of Madrid (UCM). He is a pioneer researcher in the field of Software Agents, co-creator of the FIPA MESSAGE and INGENIAS methodologies, and founder and director of the research group GRASIA: GRoup of Agent-based, Social and Interdisciplinary Applications at UCM. He is known for his work in the field of Artificial Intelligence, specifically in agent-oriented software engineering. He has been often cited by mainstream media, as a reference in Artificial Intelligence.

Maria Gini is an Italian and American Computer Scientist in artificial intelligence and robotics. She has considerable service to the computer science artificial intelligence community and for broadening participation in computing. She was Chair of the ACM Special Interest Group in Artificial Intelligence SIGAI from 2003 to 2010. She is currently a member of the CRA-W board.

Agent mining is an interdisciplinary area that synergizes multiagent systems with data mining and machine learning.

<span class="mw-page-title-main">Michael Wooldridge (computer scientist)</span> British computer scientist

Michael John Wooldridge is a professor of computer science at the University of Oxford. His main research interests is in multi-agent systems, and in particular, in the computational theory aspects of rational action in systems composed of multiple self-interested agents. His work is characterised by the use of techniques from computational logic, game theory, and social choice theory.

<span class="mw-page-title-main">GAMA Platform</span> Simulation platform

GAMA is a simulation platform with a complete modelling and simulation integrated development environment (IDE) for writing and experimenting spatially explicit agent-based models.

<span class="mw-page-title-main">Lyle Norman Long</span> Academic and computational scientist

Lyle Norman Long is an academic, and computational scientist. He is a Professor Emeritus of Computational Science, Mathematics, and Engineering at The Pennsylvania State University, and is most known for developing algorithms and software for mathematical models, including neural networks, and robotics. His research has been focused in the fields of computational science, computational neuroscience, cognitive robotics, parallel computing, and software engineering.

Robotics engineering is a branch of engineering that focuses on the conception, design, manufacturing, and operation of robots. It involves a multidisciplinary approach, drawing primarily from mechanical, electrical, software, and artificial intelligence (AI) engineering.

References

  1. ↑ Yoav Shoham, Kevin Leyton-Brown. Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations. Cambridge University Press, 2009. http://www.masfoundations.org/
  2. ↑ Hu, J.; Turgut, A.; Lennox, B.; Arvin, F., "Robust Formation Coordination of Robot Swarms with Nonlinear Dynamics and Unknown Disturbances: Design and Experiments" IEEE Transactions on Circuits and Systems II: Express Briefs, 2021.
  3. ↑ Stefano V. Albrecht, Filippos Christianos, Lukas Schäfer. Multi-Agent Reinforcement Learning: Foundations and Modern Approaches. MIT Press, 2024. https://www.marl-book.com/
  4. 1 2 3 Li, Guohao (2023). "Camel: Communicative agents for "mind" exploration of large language model society" (PDF). Advances in Neural Information Processing Systems. 36: 51991–52008. arXiv: 2303.17760 . S2CID   257900712.
  5. ↑ Niazi, Muaz; Hussain, Amir (2011). "Agent-based Computing from Multi-agent Systems to Agent-Based Models: A Visual Survey" (PDF). Scientometrics. 89 (2): 479–499. arXiv: 1708.05872 . doi:10.1007/s11192-011-0468-9. hdl:1893/3378. S2CID   17934527.
  6. ↑ Rogers, Alex; David, E.; Schiff, J.; Jennings, N.R. (2007). "The Effects of Proxy Bidding and Minimum Bid Increments within eBay Auctions". ACM Transactions on the Web. 1 (2): 9–es. CiteSeerX   10.1.1.65.4539 . doi:10.1145/1255438.1255441. S2CID   207163424. Archived from the original on April 2, 2010. Retrieved March 18, 2008.
  7. ↑ Schurr, Nathan; Marecki, Janusz; Tambe, Milind; Scerri, Paul; Kasinadhuni, Nikhil; Lewis, J.P. (2005). "The Future of Disaster Response: Humans Working with Multiagent Teams using DEFACTO". Archived (PDF) from the original on June 3, 2013. Retrieved January 8, 2024.
  8. ↑ Genc, Zulkuf; et al. (2013). "Agent-Based Information Infrastructure for Disaster Management" (PDF). Intelligent Systems for Crisis Management. Lecture Notes in Geoinformation and Cartography. pp. 349–355. doi:10.1007/978-3-642-33218-0_26. ISBN   978-3-642-33217-3.
  9. ↑ Hu, Junyan; Bhowmick, Parijat; Lanzon, Alexander (2020). "Distributed Adaptive Time-Varying Group Formation Tracking for Multiagent Systems With Multiple Leaders on Directed Graphs". IEEE Transactions on Control of Network Systems. 7: 140–150. doi: 10.1109/TCNS.2019.2913619 . S2CID   149609966.
  10. ↑ Sun, Ron; Naveh, Isaac (June 30, 2004). "Simulating Organizational Decision-Making Using a Cognitively Realistic Agent Model". Journal of Artificial Societies and Social Simulation.
  11. 1 2 Kubera, Yoann; Mathieu, Philippe; Picault, Sébastien (2010), "Everything can be Agent!" (PDF), Proceedings of the Ninth International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS'2010): 1547–1548
  12. ↑ Russell, Stuart J.; Norvig, Peter (2003), Artificial Intelligence: A Modern Approach (2nd ed.), Upper Saddle River, New Jersey: Prentice Hall, ISBN   0-13-790395-2
  13. ↑ Salamon, Tomas (2011). Design of Agent-Based Models. Repin: Bruckner Publishing. p. 22. ISBN   978-80-904661-1-1.
  14. ↑ Weyns, Danny; Omicini, Amdrea; Odell, James (2007). "Environment as a first-class abstraction in multiagent systems". Autonomous Agents and Multi-Agent Systems. 14 (1): 5–30. CiteSeerX   10.1.1.154.4480 . doi:10.1007/s10458-006-0012-0. S2CID   13347050.
  15. ↑ Wooldridge, Michael (2002). An Introduction to MultiAgent Systems. John Wiley & Sons. p. 366. ISBN   978-0-471-49691-5.
  16. ↑ Panait, Liviu; Luke, Sean (2005). "Cooperative Multi-Agent Learning: The State of the Art" (PDF). Autonomous Agents and Multi-Agent Systems. 11 (3): 387–434. CiteSeerX   10.1.1.307.6671 . doi:10.1007/s10458-005-2631-2. S2CID   19706.
  17. ↑ "The Multi-Agent Systems Lab". University of Massachusetts Amherst . Retrieved October 16, 2009.
  18. ↑ Albrecht, Stefano; Stone, Peter (2017), "Multiagent Learning: Foundations and Recent Trends. Tutorial", IJCAI-17 conference (PDF)
  19. ↑ Cucker, Felipe; Steve Smale (2007). "The Mathematics of Emergence" (PDF). Japanese Journal of Mathematics. 2: 197–227. doi:10.1007/s11537-007-0647-x. S2CID   2637067 . Retrieved June 9, 2008.
  20. ↑ Shen, Jackie (Jianhong) (2008). "Cucker–Smale Flocking under Hierarchical Leadership". SIAM J. Appl. Math. 68 (3): 694–719. arXiv: q-bio/0610048 . doi:10.1137/060673254. S2CID   14655317 . Retrieved June 9, 2008.
  21. ↑ Ahmed, S.; Karsiti, M.N. (2007), "A testbed for control schemes using multi agent nonholonomic robots", 2007 IEEE International Conference on Electro/Information Technology, p. 459, doi:10.1109/EIT.2007.4374547, ISBN   978-1-4244-0940-2, S2CID   2734931
  22. ↑ Yang, Lidong; Li, Zhang (2021). "Motion control in magnetic microrobotics: From individual and multiple robots to swarms". Annual Review of Control, Robotics, and Autonomous Systems. 4: 509–534. doi:10.1146/annurev-control-032720-104318. S2CID   228892228.
  23. ↑ "OMG Document – orbos/97-10-05 (Update of Revised MAF Submission)". www.omg.org. Retrieved February 19, 2019.
  24. ↑ Ahmed, Salman; Karsiti, Mohd N.; Agustiawan, Herman (2007). "A development framework for collaborative robots using feedback control" . Retrieved January 8, 2024.
  25. ↑ "IEEE IES Technical Committee on Industrial Agents (TC-IA)". tcia.ieee-ies.org. Retrieved February 19, 2019.
  26. ↑ "CAMEL: Finding the Scaling Law of Agents. The first and the best multi-agent framework". GitHub .
  27. ↑ Leitão, Paulo; Karnouskos, Stamatis (March 26, 2015). Industrial agents : emerging applications of software agents in industry. Leitão, Paulo,, Karnouskos, Stamatis. Amsterdam, Netherlands. ISBN   978-0128003411. OCLC   905853947.{{cite book}}: CS1 maint: location missing publisher (link)
  28. ↑ "Film showcase". MASSIVE . Retrieved April 28, 2012.
  29. ↑ Leitao, Paulo; Karnouskos, Stamatis; Ribeiro, Luis; Lee, Jay; Strasser, Thomas; Colombo, Armando W. (2016). "Smart Agents in Industrial Cyber–Physical Systems". Proceedings of the IEEE. 104 (5): 1086–1101. doi:10.1109/JPROC.2016.2521931. hdl: 10198/15438 . ISSN   0018-9219. S2CID   579475.
  30. ↑ Xiao-Feng Xie, S. Smith, G. Barlow. Schedule-driven coordination for real-time traffic network control. International Conference on Automated Planning and Scheduling (ICAPS), São Paulo, Brazil, 2012: 323–331.
  31. ↑ Máhr, T. S.; Srour, J.; De Weerdt, M.; Zuidwijk, R. (2010). "Can agents measure up? A comparative study of an agent-based and on-line optimization approach for a drayage problem with uncertainty". Transportation Research Part C: Emerging Technologies. 18 (1): 99–119. Bibcode:2010TRPC...18...99M. CiteSeerX   10.1.1.153.770 . doi:10.1016/j.trc.2009.04.018.
  32. ↑ Kazemi, Hamidreza; Liasi, Sahand; Sheikh-El-Eslami, Mohammadkazem (November 2018). "Generation Expansion Planning Considering Investment Dynamic of Market Participants Using Multi-agent System". 2018 Smart Grid Conference (SGC). pp. 1–6. doi:10.1109/SGC.2018.8777904. ISBN   978-1-7281-1138-4 . Retrieved January 8, 2024.
  33. ↑ Singh, Vijay; Samuel, Paulson (June 6, 2017). "Distributed Multi -Agent System Based Load Frequency Control for Multi- Area Power System in Smart Grid". IEEE Transactions on Industrial Electronics. 64 (6): 5151–5160. doi:10.1109/TIE.2017.2668983 . Retrieved January 8, 2024.
  34. 1 2 "AI can predict your future behaviour with powerful new simulations". New Scientist.
  35. ↑ Gong, Xiaoqian; Herty, Michael; Piccoli, Benedetto; Visconti, Giuseppe (May 3, 2023). "Crowd Dynamics: Modeling and Control of Multiagent Systems". Annual Review of Control, Robotics, and Autonomous Systems. 6 (1): 261–282. doi: 10.1146/annurev-control-060822-123629 . ISSN   2573-5144.
  36. ↑ Hallerbach, S.; Xia, Y.; Eberle, U.; Koester, F. (2018). "Simulation-Based Identification of Critical Scenarios for Cooperative and Automated Vehicles". SAE International Journal of Connected and Automated Vehicles. 1 (2). SAE International: 93. doi:10.4271/2018-01-1066.
  37. ↑ Madrigal, Story by Alexis C. "Inside Waymo's Secret World for Training Self-Driving Cars". The Atlantic. Retrieved August 14, 2020.
  38. ↑ Connors, J.; Graham, S.; Mailloux, L. (2018). "Cyber Synthetic Modeling for Vehicle-to-Vehicle Applications". In International Conference on Cyber Warfare and Security. Academic Conferences International Limited: 594-XI.

Further reading

This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.