Abstract
One problem in the design of multi-agent systems is the difficulty of predicting the occurrences that one agent might face, also to recognize and to predict their optimum behavior in these situations. Therefore, one of the most important characteristic of the agent is their ability during adoption, to learn, and correct their behavior. With consideration of the continuously changing environment, the back and forth learning of the agents, the inability to see the agent’s action first hand, and their chosen strategies, learning in a multi-agent environment can be very complex. On the one hand, with recognition to the current learning models that are used in deterministic environment that behaves linearly, which contain weaknesses; therefore, the current learning models are unproductive in complex environments that the actions of agents are stochastic. Therefore, it is necessary for the creation of learning models that are effective in stochastic environments. Purpose of this research is the creation of such a learning model. For this reason, the Hopfield and Boltzmann learning algorithms are used. In order to demonstrate the performance of their algorithms, first, an unlearned multi-agent model is created. During the interactions of the agents, they try to increase their knowledge to reach a specific value. The predicated index is the number of changed states needed to reach the convergence. Then, the learned multi-agent model is created with the Hopfield learning algorithm, and in the end, the learned multi-agent model is created with the Boltzmann learning algorithm. After analyzing the obtained figures, a conclusion can be made that when learning impose to multi-agent environment the average number of changed states needed to reach the convergence decreased and the use of Boltzmann learning algorithm decreased the average number of changed states even further in comparison with Hopfield learning algorithm due to the increase in the number of choices in each situation. Therefore, it is possible to say that the multi-agent systems behave stochastically, the more closer they behave to their true character, the speed of reaching the global solution increases.
Similar content being viewed by others
References
Ren Z, Anumba CJ (2003) Learning in multi-agent systems: a case study of construction claims negotiation. Advanc Eng Inf 16:265–275
Conitzer V, Sandholm T (2006) AWESOME: a general multiagent learning algorithm that converges in self—platy and learns a best response against stationary opponents. Mach Learn 67:23–43
Miller J (1993) The educational spectrum: orientation to curriculum. Longman, New York
Vidal JM (2007) Fundamentals of multiagent systems with netlogo examples, pp 19–38, 61–78
Alonso E, d’ Inverno M, kudenko D, Luck M, Noble J (2001) Learning in multi-agent systems. Knowl Eng Rev 16(3):277–284
Banerjee B, Peng J (2004). Performance bounded reinforcement learning in strategic interactions. American Association for Artificial Intelligence, pp 2–7
Carmel D, Markovitch S (1999) Exploration strategies for model-based learning in multi-agent systems. Auton Agent Multi Agent Syst 2:141–172
Busoniu L, Babuska R, Schutter BD (2008) A comprehensive survey of multiagent reinforcement learning. IEEE Trans Syst Man Cybern c Appl Rev 38(2):156–172
Dam N Discussion of learning algorithms in stochastic games. Computer Science Department, Iowa State University, Ames, IA. p 50010
Shoham Y, Powers R, Grenager T (2004) On the agenda(s) of research on multi-agent learning. Stanford University, Stanford
Chang Y, Kaelbling LP (2001) Playing is believing: the role of beliefs in multi-agent learning. In: Proceedings of NIPS. MIT Press, Cambridge
Powers R, Shoham Y, Vu T (2007) A general criterion and an algorithmic framework for learning in multi-agent systems. Mach Learn 67:45–76
Powers R, Shoham Y (2005) New criteria and a new algorithm for learning in multi-agent systems. Computer Science Department, Stanford University, Stanford
Russell SJ, Norvig P (2003) Artificial intelligence a modern approach. Prentice Hall, New Jersey
Wooldridge M (1996) An introduction to multiagent systems. Wiley, England, pp 105–125, 190–220
Stone P, Veloso M (2000) Multiagent systems: a survey from a machine learning perspective, Auton Robotics 8(3):345–383
Nourafza N, Setayeshi S (2008) Learning based on genetic algorithm and fuzzy genetic. In: National conference of information Technology, Islamic Azad University, Najafabad, Iran
Nourafza N, Setayeshi S, Rahman A (2009) Identifying models and algorithms learning chalenges in multi-agent systems. In: Proceeding of the first Iranian national conference on software engineering, Islamic Azad University, Roudehen, Iran
Ben-David S, Kushilevitz E, Mansour Y (1997) Online learning versus offline learning. Mach learn 29:45–63
Freeman JA, Skapura DM (1991) Neural networks algorithms, applications, and programming techniques. Addison-Wesley Publication Company, California
Beale R, Jackson T (1990) Introduction to neural networks. Institute of Physics Publishing, Bristol and Philadelphia
Haykin S (1999) Neural networks a comprehensive foundation. Prentice Hall, London
Zhang P (2000) Neural networks in optimization. Springer, New York
Hopfield JJ (1984) Neurons with graded response have collective computational properties like those of two-state neurons. Proc Natl Acad Sci USA 81:3088–3092
Hopfield JJ (1982) Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci USA 79:2554–2558
Ackley DH, Hinton GE, Sejnowski TJ (1985) A learning algorithm for Boltzmann machine. Cogn Sci 9:147–169
Kirkpatrick S, Gelatt CD, Vecchi MP (1983) Optimization by simulated annealing. Science 220:671–680
Krose B, Smagt P (1996) An introduction to neural networks
Fyfe C (1996) Artificial neural networks. Lecture notes
Anderson D, McNeill G (1992) Artificial neural networks technology. DACS report
Fausett L (1994) Fundamentals of neural networks, architectures, algorithms, and applications. Prentice-Hall, London
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Nourafza, N., Setayeshi, S. & Khadem-Zadeh, A. A novel approach to accelerate the convergence speed of a stochastic multi-agent system using recurrent neural nets. Neural Comput & Applic 21, 2015–2021 (2012). https://doi.org/10.1007/s00521-011-0624-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-011-0624-4