Cognitive Agent

A Cognitive Agent is an intelligent agent (with cognitive skill) who can perform a cognitive task and process information adaptively.

• Context:
  • It can (typically) contain an Inductive Reasoning System for pattern recognition.
  • It can (typically) contains a Deductive Reasoning System for logical inference.
  • It can (typically) have a Learning Ability for knowledge acquisition.
  • It can (typically) have a Cognition System (such as a brain) for information processing.
  • ...
  • It can often contain an Abductive Reasoning System for hypothesis generation.
  • It can often be supported by a Cognitive Operating System for mental operations.
  • It can often make Cognitive Agent Decisions that lead to Cognitive Agent Actions.
  • It can often be a Linguistic Agent capable of symbol manipulation.
  • It can often develop Mental Models of its environment.
  • ...
  • It can range from being a Conscious Agent (and approximate Human Intellectual Abilities) to being a Non-Conscious Cognitive Agent.
  • It can range from being a Living Cognitive Agent to being a Mechanical Cognitive Agent.
  • It can range from being an Emotional Cognitive Agent to being a Non-Emotional Cognitive Agent.
  • It can range from being a Single Domain Agent to being a General Intelligence Agent.
  • ...
  • It can have a Cognitive Agent Skill Level in various domains.
  • It can be an Introspecting System with self-awareness.
  • It can have Personal Interests driving motivation.
  • It can have a Cognitive Bias affecting decision making.
  • It can possess Theory of Mind for social cognition.
  • It can develop Learning Strategys for skill acquisition.
  • ...
• Examples:
  • Biological Agents, such as:
    • Human Beings with natural intelligence.
    • Higher Primates with cognitive capabilitys.
    • Dolphins demonstrating problem solving.
  • Artificial Agents, such as:
    • Advanced AI Systems with learning capabilitys.
    • Autonomous Robots with decision making abilities.
    • Expert Systems in specialized domains.
  • Hybrid Agents, such as:
    • Augmented Humans with cognitive enhancements.
    • Brain-Computer Interface systems.
    • Distributed Intelligence networks.
  • ...
• Counter-Examples:
  • Non-Cognitive Intelligent Agents, such as:
    • Reactive Systems without internal representations.
    • Simple Reflex Agents with fixed response patterns.
    • Instinct-Driven Organisms without learning capabilitys.
  • Non-Intelligent Systems, such as:
    • Basic Tools without adaptive behavior.
    • Static Programs without decision making.
  • ...
• See: Intelligence Type, Learning System, Decision Making Process, Knowledge Representation, Cognitive Architecture, Mental State, Information Processing System, Adaptive Behavior, Embodied Cognition, Cognitive Development.

---

---

References

2009

• (Berg-Cross, 2009) ⇒ Gary Berg-Cross. (2009). “Is An Agent Theory of Mind (ToM) Valuable for Adaptive, Intelligent Systems?.” In: Proceedings of the 9th Workshop on Performance Metrics for Intelligent Systems. doi:10.1145/1865909.1865936
  • QUOTE: Formalized as a ToM theory these propose alternative inherited or acquired paths by which a particular cognitive capacity may arise in a cognitive agent (children) so they understand and predict external behavior of others by attributing unobservable mental states, such as beliefs, desires and intentions.

2002

• (Riegler, 2002) ⇒ Alexander Riegler. (2002). “When is a Cognitive System Embodied?.” In: Cognitive Systems Research Journal, 3(3). doi:10.1016/S1389-0417(02)00046-3
  • QUOTE: For cognitive systems, embodiment appears to be of crucial importance.

---