These days I searched about Intelligent Agents, and found that there are classes of Intelligent Agents such as:

  • simple reflex agents
  • model-based reflex agents
  • goal-based agents
  • utility-based agents
  • learning agents

And there were diagrams about each class of IA, about how each type works by getting percepts from sensors and acting on the environment by effectors, with a special process inbetween.

And I think that IA concepts, described on those sites I've searched, were very abstract and I'd like to have:

  1. Some examples about each class of IA.
  2. Optional: Some compact definition of each class.

It will be helpful to compare and visualize those IA classes, and to understand well about what their working diagrams describe.


There's no distinguishable hardware examples for each IA class. Same mobile robot architecture with proper sensors can be implemented to behave as any IA class. The way you can determine the class of an intelligent agent is from the way it process the percept, Based on chapter 2 of Artificial Intelligent: A Modern Approach I will try to give a concise explanation for each class:

Simple Reflex agents: Takes action based on only the current environment situation it maps the current percept into proper action ignoring the history of percepts.The mapping process could be simply a table-based or by any rule based matching algorithm. Example of this class is a robotic vacuum cleaner that deliberate in an infinite loop, each percept contains a state of a current location [clean] or [dirty] and accordingly it decides whether to [suck] or [continue-moving].

Model-based Reflex agents: Needs memory for storing the percept history, it uses the percept history to help revealing the current unobservable aspects of the environment. example of this IA class is the self-steering mobile vision where it's necessary to check the percept history to fully understand how the world is evolving.

Goal-based Reflex agents: This kind of IA has a goal and has a strategy to reach that goal, All actions are based on its goal and from a set of possible actions it selects the one that improves the progress towards goal (not necessarily the best one). Example of this IA class is any searching robots that has initial location and want to reach a destination.

Utility-based Reflex agents: Like the Goal-based agent but with a measure of "how much happy" an action would make me rather than the goal-based binary feedback ['happy','unhappy'], this kind of agents provide the best solution, an example is the route recommendation system which solves for the 'best' route to reach a destination.

Learning agents: The essential component of autonomy, this agent is capable of learning from experience, it has the capability of automatic information acquisition and integration into the system, any agent designed and expected to be successful in an uncertain environment is considered to be learning agent.

  • 2
    $\begingroup$ I appreciate this answer. It provides a brief but detailed description of the classes of intelligent agents. $\endgroup$ – Seth Simba Jan 19 '18 at 7:38

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.