Agent architecture explained

Agent architecture in computer science is a blueprint for software agents and intelligent control systems, depicting the arrangement of components. The architectures implemented by intelligent agents are referred to as cognitive architectures.^[1] The term agent is a conceptual idea, but not defined precisely. It consists of facts, set of goals and sometimes a plan library.^[2]

Types

Reactive architectures

• Subsumption

Deliberative reasoning architectures

• Procedural reasoning system (PRS)

Layered/hybrid architectures

• 3T
• AuRA
• Brahms
• GAIuS
• GRL
• ICARUS
• InteRRaP
• TinyCog
• TouringMachines

Cognitive architectures

• ASMO
• Soar
• ACT-R
• Brahms
• LIDA
• PreAct
• Cougaar
• PRODIGY
• FORR

See also

• Action selection
• Cognitive architecture
• Real-time Control System

Notes and References

1. http://hri.cogs.indiana.edu/publications/aaai04ws.pdf Comparison of Agent Architectures
2. Book: Leon Sterling. Kuldar Taveter. The Art of Agent-oriented Modeling. 2009. MIT Press. 978-0-262-01311-6. 145–.