Intelligent Agents

 Exploring the fundamental concepts and

characteristics of intelligent agents.

 Analyzing their components.

 How it work.

 Agent types.

 Environment.

 Advantages of AI agent.
Introduction

• An autonomous AI agent is an advanced software program that can operate independently

without human control. It can think, act, and learn on its own, without needing constant input

from humans.

• These agents are widely used in different industries, like healthcare, finance, and banking, to

make things run smoother and more efficiently.

• They can adjust to new situations, learn from their experiences, and make decisions using

their own internal systems.

What is an intelligent agent?

• An intelligent agent is a system capable of autonomous interaction with its environment, taking actions

that maximize its success in achieving its goals.

• AI program is an intelligent agent.

• AI agent is a software program designed to interact with its environment, perceive the data it receives

through sensors, and take actions based on that data through actuators to achieve specific goals.

• AI agents simulate intelligent behavior.

• AI agents can be as simple as rule-based systems or as complex as advanced machine learning

models. They use predetermined rules or trained models to make decisions.

The components of an intelligent agent:

The building blocks of an intelligent agent are:

 Performance measure: An objective evaluation of the agent's success.

 Environment: The dynamic world the agent operates within.

 Actuators: Physical mechanisms enabling the agent to act on its environment.

 Sensors: Sensory organs facilitating perception of the surrounding environment.

 Decision-making mechanism: is the brain of an AI agent. It processes the information

gathered by the sensors and decides what action to take using the actuators.
The components of an Intelligent Agent
How does AI agents work ?

 Perceiving the environment: An autonomous AI agent first needs to gather information

about its environment. It can do so using sensors or collecting data from various sources.

 Processing input data: The agent takes the knowledge gathered in Step 1 and prepares it

for processing. This may include organizing the data, creating a knowledge base, or making

internal representations that the agent can understand and work with.
 How does AI agents work ?

 Decision-making: The agent uses reasoning techniques like logic or statistical analysis to

make an informed decision based on its knowledge base and goals.

 Executing an action: The agent makes a step or a series of steps to reach its goals.

 Learning and Improvement: After taking action, the agent can learn from its own

experiences. This feedback loop allows the agent to improve performance and adapt to new

situations and environments.

 Examples of Agents

• Human
 eyes, ear, skin, taste buds, etc. for sensors.
 hands, fingers, legs, mouth for effectors.

• Robots
 Camera, infrared, etc. for sensors.
 grippers, wheels, lights, speakers, etc. for actuators.

• Software agent
 functions as sensors.
 functions as actuators.
Key characteristics of intelligent agents include:

 Autonomy: Ability to act independently without human intervention.

 Reactivity: Real-time perception (senses and interprets the environment) and response to

environmental changes to achieve its goals.

 Pro-activeness: planning for future scenarios (Gaming).

 Socialness: Interaction with other agents or humans using different methods, like understanding

and responding to natural language, recognizing speech.

 Learning: They can learn and enhance their performance through machine, deep, and

reinforcement learning elements and techniques evolving based on experiences and environmental

shifts.
Rational Agent

What is rational at any given time depends on four things:

 The performance measure that defines the criterion of success.

 The agent’s prior knowledge of the environment.

 The actions that the agent ca n perform.

 The agent’s percept sequence to date.

This leads to a definition of a rational agent:

Rational agent should select an action that is expected to maximize its performance

measure, given the evidence provided by the percept sequence and whatever built-in

knowledge the agent has.

 Environment
The environment plays a crucial role in shaping how an intelligent agent behaves.

The nature of the task environment directly affects the appropriate design for the agent program.

Environmental characteristics like:

Fully Observable VS. Partial Observable: If an agent’s sensors give it access to the complete state

of the environment at each point in time, then we say that the task environment is fully

observable. Fully observable environments are convenient because the agent need not maintain

any internal state to keep track of the world. An environment might be partially observable

because of noisy and inaccurate sensors or because parts of the state are simply missing from the

sensor data. If the agent has no sensors at all then the environment is unobservable.
 Environmental Characteristics

SINGLE-AGENT VS. MULTIAGENT: The distinction between single-agent and multi-agent

environments may seem simple enough. For example, an agent solving a crossword puzzle by itself

is clearly in a single-agent environment, whereas an agent playing chess is in a two agent

environment (chess is a competitive multi-agent environment where as taxi-driving is a cooperative

multi-agent environment).

Deterministic vs. nondeterministic: If the next state of the environment is completely determined by

the current state and the action exec uted by the agent(s), then we say the environment is

deterministic; otherwise, it is nondeterministic.

 Environmental Characteristics

An agent need not worry about uncertainty in a fully observable, deterministic environment. Ifthe

environment is partially observable, however, then it could appear to be nondeterministic.

Taxi driving is clearly nondeterministic in this sense, because one can never predict the behavior
of traffic, moreover, one’s tires may blow out unexpectedly. The vacuum world as we described

it is deterministic, but variations can include nondeterministic elements such as randomly

appearing dirt.
 Environmental Characteristics

EPISODIC VS. SEQUENTIAL: In an episodic task environment, the agent’s experience is divided into

atomic episodes. In each episode the agent receives a percept and then performs a single

action. The next episode does not depend on the actions taken in previous episodes (Arm Robot).

In sequential environments, the current decision could affect all future decisions such as Chess

and taxi driving are sequential.

Episodic environments are much simpler than sequential environments because the agent does

not need to think ahead.

 Environmental Characteristics

DISCRETE VS. CONTINUOUS: The discrete/continuous distinction applies to the state of the

environment, to the way time is handled, and to the percepts and actions of the agent. For

example, the chess environment has a finite number of distinct states (excluding the clock).

Chess also has a discrete set of percepts and actions. Taxi driving is a continuous-state and

continuous-time problem: the speed and location of the taxi and of the other vehicles sweep

through a range of continuous values and do so smoothly over time. Taxi-driving actions are

also continuous.
 Environmental Characteristics

STATIC VS. DYNAMIC: Static environments are easy to deal with because the agent need not

keep looking at the world while it is deciding on an action, nor need it worry about the

passage of time. Dynamic environments, are continuously asking the agent what it wants to

do. Taxi driving is clearly dynamic where Crossword puzzles are static .
 The Structure of Agents

Agent =architecture +program .

Agent program take the current percept as input from the sensors and return an action

to the actuators.

The key challenge for AI is to find out how to write programs that, to the extent possible,

produce rational behavior.

 What are the types of AI agents?

 Simple reflex agents

These agents select actions on the basis of the current percept, ignoring the rest of the
percept history. For example, the vacuum agent.

we have written the agent program using if-then-else statements, it is simple enough that it
can also be implemented as a Boolean circuit.
 The types of AI agents

 Model-based reflex agents

First, we need some information about how the world changes over time.
Second, we need some information about how the state of the world is reflected in the
agent’s percepts. For example, when the car in front initiates braking.
 The types of AI agents

 Goal-based agents
Knowing something about the current state of the environment is not always enough to decide what
to do, as well as a current state description, the agent needs some sort of goal information that
describes situations that are desirable being at a particular destination. For example, at a road
junction, the taxi can turn left, turn right, or go straight on. The correct decision depends on where the
taxi is trying to get to.
 The types of AI agents

 Utility-based agents (Happy-based agents):

Goals alone are not enough to generate high-quality behavior in most environments.
when there are conflicting goals, only some of which can be achieved (for example,
speed and safety), the utility function specifies the appropriate (rational) decision. The
goals are inadequate but a utility-based agent can still make rational decisions.
 The types of AI agents

 Learning agents execute machine learning techniques to improve their decision-making over

time.
What are the advantages of using AI agents?

 Increased efficiency

AI agents c an automate repetitive tasks, allowing businesses to complete them

faster and more accurately.

 Better decision-making

AI agents can analyze large amounts of data and provide valuable insights

(pattern, correlation) to support decision-making processes.

What are the advantages of using AI agents?

 Timely customer interaction

AI agents can provide personalized and timely interactions with customers,

enhancing their experience (provide recommendations, leading to increased

customer satisfaction).

 Cost savings and avoid human errors

By automating tasks, AI agents can reduce the need for human resources and manual

labor, resulting in cost savings for businesses. They can handle high-volume, repetitive

tasks without fatigue or errors.

 Examples of AI Applications

Healthcare: AI agents can assist in diagnosing, treating, and monitoring patients (IBM Watson

Health).

Finance: They can analyze financial data, detect fraud, and make investment

recommendations (Intelligent Portfolio).

Agriculture: AI agents can optimize crop production, monitor soil quality, and predict weather

patterns. John Deere uses an AI agent called (See & Spray) to detect and target weeds

without affecting crops.

Education: They can provide personalized learning experiences, automate administrative

tasks, and analyze student performance. Pearson’s AI agent, Aida, can provide feedback to

students and suggest personalized learning paths.

 Intelligent Agents

 Must be sense.

 Must be act.

 Must be autonomous (to some extent).

 Must be rational.