A Novel Method of Constructing ANN

Artificial Neural Networks (ANNs) are powerful computational and modeling tools, however there are still some limitations in ANNs. In this paper, we give a new method to construct artificial neural network, which based on multi-agent theory and Reinforcement learning algorithm. All nodes in this new neural networks are presented as agents, and these agents have learning ability via implementing reinforcement learning algorithm. The experiment results show this method is effective.

[1]  Robert J. Schalkoff,et al.  Artificial neural networks , 1997 .

[2]  Peter Dayan,et al.  Technical Note: Q-Learning , 2004, Machine Learning.

[3]  Peter Dayan,et al.  Q-learning , 1992, Machine Learning.

[4]  Michael L. Littman,et al.  Markov Games as a Framework for Multi-Agent Reinforcement Learning , 1994, ICML.

[5]  Nicholas R. Jennings,et al.  A Roadmap of Agent Research and Development , 2004, Autonomous Agents and Multi-Agent Systems.

[6]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[7]  Manuela M. Veloso,et al.  Multiagent learning using a variable learning rate , 2002, Artif. Intell..

[8]  Michael L. Littman,et al.  Friend-or-Foe Q-learning in General-Sum Games , 2001, ICML.