Intelligent Agents and Types of

Agents

Artificial Intelligence

Narayan Furmalkar (19)

Rohit Kulkarni (33)
Rutuja More (37)
Akash Sirsat (51)
Tukaram Shinde (49)
 Index
 Introduction

 PEAS Model

 Types of intelligent agents

 Simple Reflex Agent

 Model Based Reflex Agent

 Goal Based Agent

 Utility Based Agent

 Learning Agent

 Conclusion

 References
 Introduction
 An intelligent agent (IA) is an entity that makes a decision, that enables
artificial intelligence to be put into action
 It can also be described as a software entity that conducts operations
in the place of users or programs after sensing the environment
 It uses actuators to initiate action in that environment.
 The two main functions of intelligent agents include perception and
action.
 Perception is done through sensors while actions are initiated through
actuators
 Examples:
 A software agent has Keystrokes, file contents, received network packages
which act as sensors and displays on the screen, files, sent network
packets acting as actuators.
 A Human-agent has eyes, ears, and other organs which act as sensors, and
hands, legs, mouth, and other body parts acting as actuators. 
 A Robotic agent has Cameras and infrared range finders which act as
sensors and various motors acting as actuators. 
 Introduction

Image source:
https://www.tutorialspoint.com/artificial_intelligence/images/agent_en
vironment.jpg
 Introduction
 Before Moving forward we must know elements of Agents:
– Sensor: Sensor is a device which detects the change in the
environment and sends the information to other electronic
devices. An agent observes its environment through sensors.
– Actuators: Actuators are the component of machines that converts
energy into motion. The actuators are only responsible for moving
and controlling a system. An actuator can be an electric motor,
gears, rails, etc.
– Effectors: Effectors are the devices which affect the environment.
Effectors can be legs, wheels, arms, fingers, wings, fins, and display
screen.
 Structure of Intelligent Agent:
I. Architecture:  It is a device with sensors and actuators, for
example, a robotic car, a camera, a PC. 
II. Agent Program: is an implementation of an agent function.
III.Agent Function: Agent Function helps in mapping all the
information it has gathered from the environment into action
 PEAS Model
 PEAS is a type of model on which an AI agent works upon
 PEAS can also be considered as factors which each intelligent agent
must posses.
• P: Performance
• E: Environment
• A: Actuators
• S: Sensors
 Types of Intelligent Agents
 There are basically 5 types of Intelligent Agents.
 This grouping is based on their capabilities and level of perceived
intelligence.
 Following are the types:
 Simple Reflex Agents
 Model Based Reflex Agents
 Goal Based Agents
 Utility Based Agents
 Learning Agents
 Types of Intelligent Agents
 Simple Reflex Agent:
 It acts only on the basis of the current perception
 It ignores the rest of the perception history
 It operates simply on the basis of “If-Then” Rules
 It works efficiently only in case of fully observable environment

 Problems with Simple Reflex Agents:

 Very limited intelligence
 If there occurs any change in the environment, then the
collection of rules need to be updated.
 can’t operate in partially observable environment
 Types of Intelligent Agents

Image Source:
Agents in Artificial Intelligence - GeeksforGeeks
 Types of Intelligent Agents
 Model Based Reflex Agent:
 The agent which performs actions based on current input as well
as the previous input is called as Model Based Reflex Agent.
 A Simple Reflex agent does not succeed in a partially observable
environments. Thus, to overcome its limitations, this agent is
designed.
 The reason for the success of a this agent is – the agent maintains
some sort of internal state.
 The internal state depends upon the percept history and thus
reflects atleast some of the unobserved aspects of the current
state.
 In order to maintain the internal state of the world, an agent must,
 Know how agent’s own actions affect the world. ( Eg. : If the agent
turns the steering clockwise, the car is bound to move towards the
right).
 Types of Intelligent Agents
Model Based Reflex Agent:
Know how the world evolves independent of an agent.
( Eg. : A car trying to overtake will generally close behind
the car than it was seconds ago)
This knowledge about “how the world works” is called as
the “Model” of the world.
 Types of Intelligent Agents
 Model Based Reflex Agent:
 Working:
 The sensor takes input from the environment.
 The agent then checks the current state of the world.
 Then, the agent checks the previous state of the world.
 The agent identifies how the world is evolving and how the
environment is affected by agent’s actions, which he had taken
earlier.
 Once these actions are verified on the basis of condition-action
rule, the appropriate action is decided and given to the
actuators.
 These actuators then perform the actions in the environment.
 Types of Intelligent Agents
 Goal Based Agent:
 Goal Based Agent expand the capabilities of the model-based
agent by having the goal information.
 The knowledge of the current state environment is not always
sufficient to decide for an agent to what to do .
 The agent needs to know its goals which describes desirables
situations.
 They choose an action so that they can achieve the goal.

 Searching & Planning.

 Types of Intelligent Agents
 Goal Based Agent:
 Eg : - Tour Planning
 Trend :- Amazon has made lots of Robot but Chinese Company
Alibaba made G Plus Robots which is useful to driverless delivery
 Purpose.
 Key factors:- PEAS
 Performance : -Safety
 Environment :- Obstacles on road. Like People are walking on
road.
 Action : - Like Moving handle in direction , breaking , etc
 Sensor : - Car alarm , Wrapper.
 Types of Intelligent Agents
 Goal Based Agent:
 Types of Intelligent Agents
 Utility Based Agent:
 These agents are similar to the goal-based agent but provide an
extra component of utility measurement which makes them
different by providing a measure of success at a given state.
 Utility-based agent act based not only goals but also the best way
to achieve the goal.
 The Utility-based agent is useful when there are multiple possible
alternatives, and an agent has to choose in order to perform the
best action.
 The utility function maps each state to a real number to check how
efficiently each action achieves the goals.
 Types of Intelligent Agents
 Utility Based Agent:
 Types of Intelligent Agents
 Learning Agent:
 A learning agent in AI is the type of agent that can learn from its
past experiences or it has learning capabilities
 It starts to act with basic knowledge and then is able to act and
adapt automatically through learning. 
 A learning agent has mainly four conceptual components, which
are: 
 Learning element: It is responsible for making improvements
by learning from the environment 
 Critic: The learning element takes feedback from critics which
describes how well the agent is doing with respect to a fixed
performance standard.
 Performance element: It is responsible for selecting external
action
 Problem Generator: This component is responsible for
suggesting actions that will lead to new and informative
experiences.
 Types of Intelligent Agents

Image Source:
Agents in Artificial Intelligence - GeeksforGeeks
 Conclusion
 So as far as now we’ve learnt Intelligent agents are nothing but
entities that percepts environment and based on situation takes a
rational action
 There are basically 5 categories of Intelligent agents based upon their
capabilities and efficiency
 Intelligent agents can be considered as any entity that makes decision
like mobile phone, s/w, machines
  An AI system is composed of an agent and its environment
 The agents act in their environment.
 The environment may contain other agents. 
 References
 Intelligent Agents in Artificial Intelligence | Engineering Education
(EngEd) Program | Section
 Agents in Artificial Intelligence – GeeksforGeeks
 Intelligent Agent | Agents in AI – Javatpoint
 Intelligent Agent in AI | Guide to What is the Intelligent Agent in AI
(educba.com)
 Model Based Reflex Agent in AI | The Polymath Blog (neelshelar.com)