What is an intelligent agent briefly explain structure and types of intelligent agents?

An intelligent agent (IA) is a computer software system that’s capable of acting independently to achieve certain goals and responding to people or events that are happening around it. It is programmed using the field of artificial intelligence (AI) called “machine learning (ML)” and equipped with sensors that allow it to observe and adapt to situations.

IAs are utilized in areas that require interacting with people because they are capable of demonstrating basic social skills. Today’s examples of IAs include Siri and Alexa. These can understand a request and act on their own to look for the information that’s being asked.

An IA can be likened to a cab driver that measures his performance based on a passenger’s safety and comfort, ability to reach the desired destination on time, and capacity to earn. He considers his environment, including the quality of the roads he takes and the traffic. He uses his car’s built-in features (e.g., brakes, accelerator, signal lights, etc.) or, in IA terms, actuators and sensors (e.g., camera, speedometer, odometer, etc.) to take the best course of action to reach his goal.

Other interesting terms…

• What is a Chatbot?
• What is Machine Learning?

Read More about an “Intelligent Agent”

How Does an Intelligent Agent Work?

IAs are classified based on their level of intelligence, but, in general, they work this way:

An IA takes various percepts or inputs from its environment, processes it using ML, and then acts as programmed or trained.

What Are the Different Types of Intelligent Agents?

As mentioned earlier, IAs are categorized based on what they can do. Five types of IAs exist, namely:

Simple reflex agent

This is the most basic type. It acts based on the current situation the machine is in. When something happens in its environment, it scans its knowledge base for possible responses to the case based on predetermined rules.

Model-based reflex agent

This type uses its built-in percept history and internal memory to make decisions about a prebuilt model of its environment. Its internal memory allows it to store some navigation history to help it understand its surroundings even if it cannot directly observe what it needs to act.

Goal-based agent

Every IA has a set of goals to respond desirably to its situation. This kind of IA uses pre-programmed actions based on their possible outcomes to meet its objectives. It can perform a single or many activities, depending on its goal.

Utility-based agent

This IA acts not only based on its goal but chooses the best way to achieve its objective, which sets it apart from the other types.

Learning agent

This type can learn from its experiences. It is prebuilt with basic knowledge but can act and adapt to situations independently to improve its performance. In short, a programmer does not need to give it all the information it needs; it works and improves all on its own.

What Characteristics Make Up an Intelligent Agent?

Nikola Kasabov and Robert Kozma, authors of “Introduction: Hybrid Intelligent Adaptive Systems,” describe IAs as devices that:

• Make room for new problem-solving rules over time
• Adapt online and in real time
• Can analyze their behaviors, errors, and successes
• Learn and improve through their interactions with their surroundings
• Learn quickly given large amounts of data
• Have memory-based exemplar storage and retrieval capacities
• Use parameters to represent short- and long-term memory, age, and forgetting, among other things

What Are Intelligent Agents Used For?

IAs can serve as automated online assistants that perceive customers’ needs to provide personalized customer service. These agents typically have a dialog system, an avatar, and an expert system that serves specialized functions. They can also optimize coordination between human groups online.

Examples, as mentioned above, include Alexa and Siri. A smart vacuum cleaner that cleans an area by moving from one tile to another is also an IA.

More from Techslang...

An AI system is composed of an agent and its environment. The agents act in their environment. The environment may contain other agents.

What are Agent and Environment?

An agent is anything that can perceive its environment through sensors and acts upon that environment through effectors.

• A human agent has sensory organs such as eyes, ears, nose, tongue and skin parallel to the sensors, and other organs such as hands, legs, mouth, for effectors.

• A robotic agent replaces cameras and infrared range finders for the sensors, and various motors and actuators for effectors.

• A software agent has encoded bit strings as its programs and actions.

Agent Terminology

• Performance Measure of Agent − It is the criteria, which determines how successful an agent is.

• Behavior of Agent − It is the action that agent performs after any given sequence of percepts.

• Percept − It is agent’s perceptual inputs at a given instance.

• Percept Sequence − It is the history of all that an agent has perceived till date.

• Agent Function − It is a map from the precept sequence to an action.

Rationality

Rationality is nothing but status of being reasonable, sensible, and having good sense of judgment.

Rationality is concerned with expected actions and results depending upon what the agent has perceived. Performing actions with the aim of obtaining useful information is an important part of rationality.

What is Ideal Rational Agent?

An ideal rational agent is the one, which is capable of doing expected actions to maximize its performance measure, on the basis of −

• Its percept sequence
• Its built-in knowledge base

Rationality of an agent depends on the following −

• The performance measures, which determine the degree of success.

• Agent’s Percept Sequence till now.

• The agent’s prior knowledge about the environment.

• The actions that the agent can carry out.

A rational agent always performs right action, where the right action means the action that causes the agent to be most successful in the given percept sequence. The problem the agent solves is characterized by Performance Measure, Environment, Actuators, and Sensors (PEAS).

The Structure of Intelligent Agents

Agent’s structure can be viewed as −

• Agent = Architecture + Agent Program
• Architecture = the machinery that an agent executes on.
• Agent Program = an implementation of an agent function.

Simple Reflex Agents

• They choose actions only based on the current percept.
• They are rational only if a correct decision is made only on the basis of current precept.
• Their environment is completely observable.

Condition-Action Rule − It is a rule that maps a state (condition) to an action.

Model Based Reflex Agents

They use a model of the world to choose their actions. They maintain an internal state.

Model − knowledge about “how the things happen in the world”.

Internal State − It is a representation of unobserved aspects of current state depending on percept history.

Updating the state requires the information about −

• How the world evolves.
• How the agent’s actions affect the world.

Goal Based Agents

They choose their actions in order to achieve goals. Goal-based approach is more flexible than reflex agent since the knowledge supporting a decision is explicitly modeled, thereby allowing for modifications.

Goal − It is the description of desirable situations.

Utility Based Agents

They choose actions based on a preference (utility) for each state.

Goals are inadequate when −

• There are conflicting goals, out of which only few can be achieved.

• Goals have some uncertainty of being achieved and you need to weigh likelihood of success against the importance of a goal.

The Nature of Environments

Some programs operate in the entirely artificial environment confined to keyboard input, database, computer file systems and character output on a screen.

In contrast, some software agents (software robots or softbots) exist in rich, unlimited softbots domains. The simulator has a very detailed, complex environment. The software agent needs to choose from a long array of actions in real time. A softbot designed to scan the online preferences of the customer and show interesting items to the customer works in the real as well as an artificial environment.

The most famous artificial environment is the Turing Test environment, in which one real and other artificial agents are tested on equal ground. This is a very challenging environment as it is highly difficult for a software agent to perform as well as a human.

Turing Test

The success of an intelligent behavior of a system can be measured with Turing Test.

Two persons and a machine to be evaluated participate in the test. Out of the two persons, one plays the role of the tester. Each of them sits in different rooms. The tester is unaware of who is machine and who is a human. He interrogates the questions by typing and sending them to both intelligences, to which he receives typed responses.

This test aims at fooling the tester. If the tester fails to determine machine’s response from the human response, then the machine is said to be intelligent.

Properties of Environment

The environment has multifold properties −

• Discrete / Continuous − If there are a limited number of distinct, clearly defined, states of the environment, the environment is discrete (For example, chess); otherwise it is continuous (For example, driving).

• Observable / Partially Observable − If it is possible to determine the complete state of the environment at each time point from the percepts it is observable; otherwise it is only partially observable.

• Static / Dynamic − If the environment does not change while an agent is acting, then it is static; otherwise it is dynamic.

• Single agent / Multiple agents − The environment may contain other agents which may be of the same or different kind as that of the agent.

• Accessible / Inaccessible − If the agent’s sensory apparatus can have access to the complete state of the environment, then the environment is accessible to that agent.

• Deterministic / Non-deterministic − If the next state of the environment is completely determined by the current state and the actions of the agent, then the environment is deterministic; otherwise it is non-deterministic.

• Episodic / Non-episodic − In an episodic environment, each episode consists of the agent perceiving and then acting. The quality of its action depends just on the episode itself. Subsequent episodes do not depend on the actions in the previous episodes. Episodic environments are much simpler because the agent does not need to think ahead.

What are the types of agents?

How many types of agents are there in intelligent systems?

What are the different types of agents in AI?

What are the four classes of intelligent agents?