Abstract

Multi-Agent systems have generated lots of excitement in recent years because of its promise as a new paradigm for conceptualizing, designing, and implementing software systems. One of the most important aspects of agent design in AI is the way agent acts or responds to the environment that the agent is acting upon. An effective action selection and behavioral method gives a powerful advantage in overall agent performance. We define a new method of action selection based on probability/priority models, we thereby introduce two efficient ways to determine probabilities using neuro-fuzzy systems and bidirectional neural networks and a new priority based system which maps the human knowledge to the action selection method. Furthermore, a behavior model is introduced to make the model more flexible.

Highlights

  • The main aspect of complex MAS domains is the way agents cooperate to achieve a common goal based on their decisions

  • Probabilistic modeling leads to modeling the uncertainty of noisy MAS domains such as RoboCup soccer server [Chen, M., et al, 2001] to logical decision making such as an action being selected

  • In [Stone, P., et al, 2000b], the authors presented a technique of action selection using soft fuzzy functions and the respected formula of psvs × (1− ps )v f where ps is the probability of success and vs and v f are the values of succeeding and failing of an action respectively

Read more

Summary

Introduction

The main aspect of complex MAS domains is the way agents cooperate to achieve a common goal based on their decisions. The action selector method combines the priority/probability results and will select the action with the highest reward. Action Generator Models action selection is based on analysis of several possible actions which are generated by the agent in each given cycle. As shown in the block diagram of the architecture, the agent has an action repository. Based on his current situation, a set of actions are activated for further consideration We define an action ACTIVE when the action’s activation method is executed in the current situation. The activation method of an action is executed if all of the action’s prerequisites are met in the current situation.

Play modes Trigger
Probability Model
Neural Network Performance
Experimental Results
Conclusion and Future Work
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.