Structure Learning of a Behavior Network for Context Dependent Adaptability

One mechanism for an intelligent agent to adapt to substantial environmental changes is to change the structure of its behavior network. In earlier work, we developed a context-dependent behavior selection architecture that uses structure change as the main mechanism to generate different behavior patterns according to different behavioral contexts. This paper investigates how the structure of such a behavior network can be learned. We present a structure learning method based on generic algorithm (GA). The results show that given a particular dynamic environment, consistent and robust structure can be learned to allow an agent to behave adaptively.

[1]  Sandip Sen,et al.  Evolving Beharioral Strategies in Predators and Prey , 1995, Adaption and Learning in Multi-Agent Systems.

[2]  Michael G. Dyer,et al.  Evolution of herding behavior in artificial animals , 1993 .

[3]  E. Gould,et al.  Dominance Hierarchy Influences Adult Neurogenesis in the Dentate Gyrus , 2004, The Journal of Neuroscience.

[4]  DH Edwards,et al.  Mutual inhibition among neural command systems as a possible mechanism for behavioral choice in crayfish , 1991, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[5]  Erfu Yang,et al.  Multiagent Reinforcement Learning for Multi-Robot Systems: A Survey , 2004 .

[6]  D. H. Edwards,et al.  Context-Dependent Structure Control for Adaptive Behavior Selection , 2007 .

[7]  Pattie Maes,et al.  A bottom-up mechanism for behavior selection in an artificial creature , 1991 .

[8]  Darran Singleton.  An Evolvable Approach to the Maes Action Selection Mechanism , 2002 .

[9]  Panos E. Trahanias,et al.  Hierarchical Cooperative CoEvolution Facilitates the Redesign of Agent-Based Systems , 2006, SAB.

[10]  Illah R. Nourbakhsh,et al.  A survey of socially interactive robots , 2003, Robotics Auton. Syst..

[11]  Barbara Dunin-Keplicz,et al.  Proceedings of the 2005 IEEE/WIC/ACM International Conference on Intelligent Agent Technology , 2005 .

[12]  Fadi A. Issa,et al.  Dominance hierarchy formation in juvenile crayfish procambarus clarkii , 1999, The Journal of experimental biology.

[13]  D. H. Edwards,et al.  The effects of social experience on the behavioral response to unexpected touch in crayfish , 2006, Journal of Experimental Biology.

[14]  Orlando Avila-García,et al.  Using Hormonal Feedback to Modulate Action Selection in a Competitive Scenario , 2004 .

[15]  R. Arkin.  Moving Up the Food Chain: Motivation and Emotion in Behavior-Based Robots , 2003 .

[16]  T. Christaller,et al.  Dual dynamics: Designing behavior systems for autonomous robots , 1998, Artificial Life and Robotics.

[17]  Carlos Delgado-Mata,et al.  Emotion and action selection: regulating the collective behaviour of agents in virtual environments , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[18]  Manuela M. Veloso,et al.  Multiagent Systems: A Survey from a Machine Learning Perspective , 2000, Auton. Robots.

[19]  Fadi A. Issa,et al.  Patterns of Neural Circuit Activation and Behavior during Dominance Hierarchy Formation in Freely Behaving Crayfish , 2001, The Journal of Neuroscience.

[20]  Michael A. Arbib,et al.  Who Needs Emotions? - The brain meets the robot , 2004, Who Needs Emotions?.

[21]  Henrik Hautop Lund,et al.  Co-evolving Complex Robot Behavior , 2003, ICES.