Abstract
The following paper introduces an evolution strategy on the basis of cooperative behaviors in each group of agents. The evolution strategy helps each agent to be self-defendable and self-maintainable. To determine an optimal group behavior strategy under dynamically varying circumstances, agents in same group cooperate with each other. This proposed method use reinforcement learning, enhanced neural network, and artificial life. In the present paper, we apply two different reward models: reward model 1 and reward model 2. Each reward model is designed as considering the reinforcement or constraint of behaviors. In competition environments of agents, the behavior considered to be advantageous is reinforced as adding reward values. On the contrary, the behavior considered to be disadvantageous is constrained as subtracting the values. And we propose an enhanced neural network to add learning behavior of an artificial organism-level to artificial life simulation. In future, the system models and results described in this paper will be applied to the framework of healthcare systems that consists of biosensors, healthcare devices, and healthcare system.
Similar content being viewed by others
References
Baldwin JM (1996) A new factor in evolution. In: Belew RK, Mitchell M (eds) Adaptive individuals in evolving populations: models and algorithms. Addison–Wesley
Collins RJ (1992) Studies in artificial evolution. Phd Thesis Philosophy in Computer Science, University of California, Los Angeles
Collins RJ, David R (1992) An artificial neural network representation for artificial organisms. In: Proceedings of the first workshop on parallel problem solving, vol 496, lecture notes in Computer Science, pp 259–263
Collins RJ, Jefferson DR (1991) Ant farm: towards simulated evolution. In: Farmer JD, Langton C, Rasmussen S, Taylor C (ed.) Artificial life II. Addison–Wesley
Dorigo M, Maniezzo V and Colorni A (1996). Ant system: optimization by a colony of cooperating agents. IEEE Trans Syst Man Cybern-Part B: Cybern 26(1): 29–41
Georgeff M (1999) A theory of action for multi-agent planning. In: Proceedings of the 1999 national conference artificial intelligence, pp 121–125
Gruau F and Whitley D (1993). Adding learning to the cellular development of neural networks: evolution and the Baldwin effect. Evol Comput I 3: 213–233
Jim K-C and Giles CL (2000). Talkin helps: evolving communicating agents for the predator-prey pursuit problem. Artif Life 6: 237–254
Kuk BH (2001). Evolution strategy of agent using artificial life. Korea Inf Sci 27(4): 142–162
Kohri T, Matsubayashi Y (2000) An adaptive architecture for modular Q-learning. In: Proceedings of the 10th international conference on simulation of adaptive behavior, MIT Press, pp 1–6
Kreifelt T, von Martial F (1991) A negotiation framework for autonomous agents. In: Demazeau Y, Muller JP (eds) Decentrilazed AI2. Elsevier Science
Lee M (2003). Evolution of behaviors in autonomous robot using artificial neural network and genetic algorithm. Inf Sci 155: 43–60
Lesser VR (1999). Cooperative multi-agent systems: a personal view of the state of the art. IEEE Transac Knowl Data Eng 11(1): 133–142
Nagayuki Y, Ishii S (1999) Multi-agent reinforcement learning: an approach based on the other agent’s internal model, from animals to animates. In: Proceedings of the 8th international conference on the simulation of adaptive behavior, MIT Press, pp 478–485
Nolfi S and Floreano D (1998). Co-evolving predator and prey agents: do ’arm races’ arise in artificial evolution. Artif Life 4(4): 311–335
Nolfi S, Elman JL, Parisi D (1990) Learning and evolution in neural networks. CRL Technical Report 9019, University of California, San Diego
Nwana HS, Lee L, Jennings NR (2001) Co-ordination in multi-agent systems. Software Agents and Soft Computing, Towards Enhancing Machine Intelligence, Concepts and Applications, Springer
Parkes DC, Ungar LH (1997) Learning and adaptation in multi-agent system. In: AAAI workshop on multi-agent learning providence, June 30
Stone P, Veloso M (2000) Multi-agent systems: a survey from a machine learning perspective. Auton Robots 8:345–383
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lee, M. A study of evolution strategy based cooperative behavior in collective agents. Artif Intell Rev 25, 195–209 (2006). https://doi.org/10.1007/s10462-007-9056-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10462-007-9056-z