Intelligent agent
Encyclopedia
In artificial intelligence
, an intelligent agent (IA) is an autonomous entity which observes through sensors and acts upon an environment
using actuators (i.e. it is an agent
) and directs its activity towards achieving goals (i.e. it is rational
). Intelligent agents may also learn
or use knowledge
to achieve their goals. They may be very simple or very complex
: a reflex machine such as a thermostat is an intelligent agent, as is a human being, as is a community of human beings working together towards a goal.
Intelligent agents are often described schematically as an abstract functional system similar to a computer program
. For this reason, intelligent agents are sometimes called abstract intelligent agents (AIA) to distinguish them from their real world implementations as computer systems, biological systems, or organizations. Some definitions of intelligent agents emphasize their autonomy, and so prefer the term autonomous intelligent agents. Still others (notably ) considered goal-directed behavior as the essence of intelligence and so prefer a term borrowed from economics
, "rational agent
".
Intelligent agents in artificial intelligence are closely related to agent
s in economics
, and versions of the intelligent agent paradigm are studied in cognitive science
, ethics, the philosophy of practical reason
, as well as in many interdisciplinary socio-cognitive
modeling
and computer social simulations.
Intelligent agents are also closely related to software agent
s (an autonomous software program that carries out tasks on behalf of users). In computer science
, the term intelligent agent may be used to refer to a software agent that has some intelligence, regardless if it is not a rational agent by Russell and Norvig's definition. For example, autonomous programs used for operator assistance or data mining (sometimes referred to as bots) are also called "intelligent agents".
Agent function is an abstract concept as it could incorporate various principles of decision making like calculation of utility
of individual options, deduction over logic rules, fuzzy logic
, etc.
The program agent, instead, maps every possible percept to an action.
We use the term percept to refer to the agent's perceptional inputs at any given instant. In the following figures an agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators.
group agents into five classes based on their degree of perceived intelligence and capability:
Simple reflex agents
Simple reflex agents act only on the basis of the current percept, ignoring the rest of the percept history. The agent function is based on the condition-action rule: if condition then action.
This agent function only succeeds when the environment is fully observable. Some reflex agents can also contain information on their current state which allows them to disregard conditions whose actuators are already triggered.
Infinite loops are often unavoidable for simple reflex agents operating in partially observable environments. Note: If the agent can randomize its actions, it may be possible to escape from infinite loops.
Model-based reflex agents
A model-based agent can handle a partially observable environment. Its current state is stored inside the agent maintaining some kind of structure which describes the part of the world which cannot be seen. This knowledge about "how the world works" is called a model of the world, hence the name "model-based agent".
A model-based reflex agent should maintain some sort of internal model
that depends on the percept history and thereby reflects at least some of the unobserved aspects of the current state. It then chooses an action in the same way as the reflex agent.
Goal-based agents
Goal-based agents further expand on the capabilities of the model-based agents, by using "goal" information. Goal information describes situations that are desirable. This allows the agent a way to choose among multiple possibilities, selecting the one which reaches a goal state. Search and planning are the subfields of artificial intelligence devoted to finding action sequences that achieve the agent's goals.
In some instances the goal-based agent appears to be less efficient; it is more flexible because the knowledge that supports its decisions is represented explicitly and can be modified.
Utility-based agents
Goal-based agents only distinguish between goal states and non-goal states. It is possible to define a measure of how desirable a particular state is. This measure can be obtained through the use of a utility function which maps a state to a measure of the utility of the state. A more general performance measure should allow a comparison of different world states according to exactly how happy they would make the agent. The term utility, can be used to describe how "happy" the agent is.
A rational utility-based agent chooses the action that maximizes the expected utility of the action outcomes- that is, the agent expects to derive, on average, given the probabilities and utilities of each outcome. A utility-based agent has to model and keep track of its environment, tasks that have involved a great deal of research on perception, representation, reasoning, and learning.
Learning agents
Learning has an advantage that it allows the agents to initially operate in unknown environments and to become more competent than its initial knowledge alone might allow. The most important distinction is between the "learning element", which is responsible for making improvements, and the "performance element", which is responsible for selecting external actions.
The learning element uses feedback from the "critic" on how the agent is doing and determines how the performance element should be modified to do better in the future.
The performance element is what we have previously considered to be the entire agent: it takes in percepts and decides on actions.
The last component of the learning agent is the "problem generator". It is responsible for suggesting actions that will lead to new and informative experiences.
, Intelligent Agents today are normally gathered in a hierarchical structure containing many “sub-agents”. Intelligent sub-agents process and perform lower level functions. Taken together, the intelligent agent and sub-agents create a complete system that can accomplish difficult tasks or goals with behaviors and responses that display a form of intelligence.
Artificial intelligence
Artificial intelligence is the intelligence of machines and the branch of computer science that aims to create it. AI textbooks define the field as "the study and design of intelligent agents" where an intelligent agent is a system that perceives its environment and takes actions that maximize its...
, an intelligent agent (IA) is an autonomous entity which observes through sensors and acts upon an environment
Environment (biophysical)
The biophysical environment is the combined modeling of the physical environment and the biological life forms within the environment, and includes all variables, parameters as well as conditions and modes inside the Earth's biosphere. The biophysical environment can be divided into two categories:...
using actuators (i.e. it is an agent
Software agent
In computer science, a software agent is a piece of software that acts for a user or other program in a relationship of agency, which derives from the Latin agere : an agreement to act on one's behalf...
) and directs its activity towards achieving goals (i.e. it is rational
Rational choice theory
Rational choice theory, also known as choice theory or rational action theory, is a framework for understanding and often formally modeling social and economic behavior. It is the main theoretical paradigm in the currently-dominant school of microeconomics...
). Intelligent agents may also learn
Machine learning
Machine learning, a branch of artificial intelligence, is a scientific discipline concerned with the design and development of algorithms that allow computers to evolve behaviors based on empirical data, such as from sensor data or databases...
or use knowledge
Knowledge representation
Knowledge representation is an area of artificial intelligence research aimed at representing knowledge in symbols to facilitate inferencing from those knowledge elements, creating new elements of knowledge...
to achieve their goals. They may be very simple or very complex
Complexity
In general usage, complexity tends to be used to characterize something with many parts in intricate arrangement. The study of these complex linkages is the main goal of complex systems theory. In science there are at this time a number of approaches to characterizing complexity, many of which are...
: a reflex machine such as a thermostat is an intelligent agent, as is a human being, as is a community of human beings working together towards a goal.
Computer program
A computer program is a sequence of instructions written to perform a specified task with a computer. A computer requires programs to function, typically executing the program's instructions in a central processor. The program has an executable form that the computer can use directly to execute...
. For this reason, intelligent agents are sometimes called abstract intelligent agents (AIA) to distinguish them from their real world implementations as computer systems, biological systems, or organizations. Some definitions of intelligent agents emphasize their autonomy, and so prefer the term autonomous intelligent agents. Still others (notably ) considered goal-directed behavior as the essence of intelligence and so prefer a term borrowed from economics
Economics
Economics is the social science that analyzes the production, distribution, and consumption of goods and services. The term economics comes from the Ancient Greek from + , hence "rules of the house"...
, "rational agent
Rational agent
In economics, game theory, decision theory, and artificial intelligence, a rational agent is an agent which has clear preferences, models uncertainty via expected values, and always chooses to perform the action that results in the optimal outcome for itself from among all feasible actions...
".
Intelligent agents in artificial intelligence are closely related to agent
Agent (economics)
In economics, an agent is an actor and decision maker in a model. Typically, every agent makes decisions by solving a well or ill defined optimization/choice problem. The term agent can also be seen as equivalent to player in game theory....
s in economics
Agent-Based Computational Economics
Agent-based computational economics is the major aspect of computational economics that studies economic processes, including whole economies, as dynamic systems of interacting agents. As such, it falls in paradigm of complex adaptive systems...
, and versions of the intelligent agent paradigm are studied in cognitive science
Cognitive science
Cognitive science is the interdisciplinary scientific study of mind and its processes. It examines what cognition is, what it does and how it works. It includes research on how information is processed , represented, and transformed in behaviour, nervous system or machine...
, ethics, the philosophy of practical reason
Practical reason
In philosophy, practical reason is the use of reason to decide how to act. This contrasts with theoretical reason , which is the use of reason to decide what to believe. For example: agents use practical reason to decide whether to build a telescope, but theoretical reason to decide which of two...
, as well as in many interdisciplinary socio-cognitive
Socio-cognitive
Socio-cognitive or sociocognitive describes integrated cognitive and social properties of systems, processes, functions, models, as well as can indicate the branch of science, engineering or technology, such as socio-cognitive research, socio-cognitive interactions.This term is especially used when...
modeling
Scientific modelling
Scientific modelling is the process of generating abstract, conceptual, graphical and/or mathematical models. Science offers a growing collection of methods, techniques and theory about all kinds of specialized scientific modelling...
and computer social simulations.
Intelligent agents are also closely related to software agent
Software agent
In computer science, a software agent is a piece of software that acts for a user or other program in a relationship of agency, which derives from the Latin agere : an agreement to act on one's behalf...
s (an autonomous software program that carries out tasks on behalf of users). In computer science
Computer science
Computer science or computing science is the study of the theoretical foundations of information and computation and of practical techniques for their implementation and application in computer systems...
, the term intelligent agent may be used to refer to a software agent that has some intelligence, regardless if it is not a rational agent by Russell and Norvig's definition. For example, autonomous programs used for operator assistance or data mining (sometimes referred to as bots) are also called "intelligent agents".
A variety of definitions
Intelligent agents have been defined many different ways. According to Nikola Kasabov IA systems should exhibit the following characteristics:- accommodate new problem solvingProblem solvingProblem solving is a mental process and is part of the larger problem process that includes problem finding and problem shaping. Consideredthe most complex of all intellectual functions, problem solving has been defined as higher-order cognitive process that requires the modulation and control of...
rules incrementally - adapt onlineONLINEONLINE is a magazine for information systems first published in 1977. The publisher Online, Inc. was founded the year before. In May 2002, Information Today, Inc. acquired the assets of Online Inc....
and in real timeReal-time computingIn computer science, real-time computing , or reactive computing, is the study of hardware and software systems that are subject to a "real-time constraint"— e.g. operational deadlines from event to system response. Real-time programs must guarantee response within strict time constraints... - be able to analyze itselfSelf-conceptSelf-concept is a multi-dimensional construct that refers to an individual's perception of "self" in relation to any number of characteristics, such as academics , gender roles and sexuality, racial identity, and many others. Each of these characteristics is a research domain Self-concept (also...
in terms of behavior, error and success. - learn and improve through interaction with the environment (embodiment)
- learn quickly from large amounts of dataData (computing)In computer science, data is information in a form suitable for use with a computer. Data is often distinguished from programs. A program is a sequence of instructions that detail a task for the computer to perform...
- have memory-based exemplar storageComputer storageComputer data storage, often called storage or memory, refers to computer components and recording media that retain digital data. Data storage is one of the core functions and fundamental components of computers....
and retrieval capacities - have parametersParameter (computer science)In computer programming, a parameter is a special kind of variable, used in a subroutine to refer to one of the pieces of data provided as input to the subroutine. These pieces of data are called arguments...
to represent short and long term memory, age, forgetting, etc.
Structure of agents
A simple agent program can be defined mathematically as an agent function which maps every possible percepts sequence to a possible action the agent can perform or to a coefficient, feedback element, function or constant that affects eventual actions:Agent function is an abstract concept as it could incorporate various principles of decision making like calculation of utility
Utility
In economics, utility is a measure of customer satisfaction, referring to the total satisfaction received by a consumer from consuming a good or service....
of individual options, deduction over logic rules, fuzzy logic
Fuzzy logic
Fuzzy logic is a form of many-valued logic; it deals with reasoning that is approximate rather than fixed and exact. In contrast with traditional logic theory, where binary sets have two-valued logic: true or false, fuzzy logic variables may have a truth value that ranges in degree between 0 and 1...
, etc.
The program agent, instead, maps every possible percept to an action.
We use the term percept to refer to the agent's perceptional inputs at any given instant. In the following figures an agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators.
Classes of intelligent agents
- simple reflex agents
- model-based reflex agents
- goal-based agents
- utility-based agents
- learning agents
Simple reflex agents
Simple reflex agents act only on the basis of the current percept, ignoring the rest of the percept history. The agent function is based on the condition-action rule: if condition then action.
This agent function only succeeds when the environment is fully observable. Some reflex agents can also contain information on their current state which allows them to disregard conditions whose actuators are already triggered.
Infinite loops are often unavoidable for simple reflex agents operating in partially observable environments. Note: If the agent can randomize its actions, it may be possible to escape from infinite loops.
Model-based reflex agents
A model-based agent can handle a partially observable environment. Its current state is stored inside the agent maintaining some kind of structure which describes the part of the world which cannot be seen. This knowledge about "how the world works" is called a model of the world, hence the name "model-based agent".
A model-based reflex agent should maintain some sort of internal model
Internal model
An internal model is a postulated neural process that simulates the response of the motor system in order to estimate the outcome of a motor command....
that depends on the percept history and thereby reflects at least some of the unobserved aspects of the current state. It then chooses an action in the same way as the reflex agent.
Goal-based agents
Goal-based agents further expand on the capabilities of the model-based agents, by using "goal" information. Goal information describes situations that are desirable. This allows the agent a way to choose among multiple possibilities, selecting the one which reaches a goal state. Search and planning are the subfields of artificial intelligence devoted to finding action sequences that achieve the agent's goals.
In some instances the goal-based agent appears to be less efficient; it is more flexible because the knowledge that supports its decisions is represented explicitly and can be modified.
Utility-based agents
Goal-based agents only distinguish between goal states and non-goal states. It is possible to define a measure of how desirable a particular state is. This measure can be obtained through the use of a utility function which maps a state to a measure of the utility of the state. A more general performance measure should allow a comparison of different world states according to exactly how happy they would make the agent. The term utility, can be used to describe how "happy" the agent is.
A rational utility-based agent chooses the action that maximizes the expected utility of the action outcomes- that is, the agent expects to derive, on average, given the probabilities and utilities of each outcome. A utility-based agent has to model and keep track of its environment, tasks that have involved a great deal of research on perception, representation, reasoning, and learning.
Learning agents
Learning has an advantage that it allows the agents to initially operate in unknown environments and to become more competent than its initial knowledge alone might allow. The most important distinction is between the "learning element", which is responsible for making improvements, and the "performance element", which is responsible for selecting external actions.
The learning element uses feedback from the "critic" on how the agent is doing and determines how the performance element should be modified to do better in the future.
The performance element is what we have previously considered to be the entire agent: it takes in percepts and decides on actions.
The last component of the learning agent is the "problem generator". It is responsible for suggesting actions that will lead to new and informative experiences.
Other classes of intelligent agents
According to other sources, some of the sub-agents (not already mentioned in this treatment) that may be a part of an Intelligent Agent or a complete Intelligent Agent in themselves are:- Decision Agents (that are geared to decision making);
- Input Agents (that process and make sense of sensor inputs - e.g. neural networkNeural networkThe term neural network was traditionally used to refer to a network or circuit of biological neurons. The modern usage of the term often refers to artificial neural networks, which are composed of artificial neurons or nodes...
based agents); - Processing Agents (that solve a problem like speech recognition);
- Spatial Agents (that relate to the physical real-world);
- World Agents (that incorporate a combination of all the other classes of agents to allow autonomous behaviors).
- Believable agents - An agent exhibiting a personality via the use of an artificial character (the agent is embedded) for the interaction.
- Physical Agents - A physical agent is an entity which percepts through sensors and acts through actuators.
- Temporal Agents - A temporal agent may use time based stored information to offer instructions or data acts to a computer program or human being and takes program inputs percepts to adjust its next behaviors.
Hierarchies of agents
To actively perform their functionsFunction (engineering)
In engineering, a function is interpreted as a specific process, action or task that a system is able to perform .-In engineering design:In the lifecycle of engineering projects, there are usually distinguished subsequently: Requirements and Functional specification documents. The Requirements...
, Intelligent Agents today are normally gathered in a hierarchical structure containing many “sub-agents”. Intelligent sub-agents process and perform lower level functions. Taken together, the intelligent agent and sub-agents create a complete system that can accomplish difficult tasks or goals with behaviors and responses that display a form of intelligence.
See also
- Agent (disambiguation)
- Cognitive architectureCognitive architectureA cognitive architecture is a blueprint for intelligent agents. It proposes computational processes that act like certain cognitive systems, most often, like a person, or acts intelligent under some definition. Cognitive architectures form a subset of general agent architectures...
s - Cognitive radioCognitive radioA cognitive radio is a kind of two-way radio that automatically changes its transmission or reception parameters, in a way where the entire wireless communication network -- of which it is a node -- communicates efficiently, while avoiding interference with licensed or licensed exempt users...
- a practical field for implementation - CyberneticsCyberneticsCybernetics is the interdisciplinary study of the structure of regulatory systems. Cybernetics is closely related to information theory, control theory and systems theory, at least in its first-order form...
, Computer scienceComputer scienceComputer science or computing science is the study of the theoretical foundations of information and computation and of practical techniques for their implementation and application in computer systems... - Data mining agent
- Embodied agent
- Federated searchFederated searchFederated search is an information retrieval technology that allows the simultaneous search of multiple searchable resources. A user makes a single query request which is distributed to the search engines participating in the federation...
- the ability for agents to search heterogeneous data sources using a single vocabulary - Fuzzy agentFuzzy agentIn computer science a fuzzy agent is a software agent that implements fuzzy logic. This software entity interacts with its environment through an adaptive rule-base and can therefore be considered as a type of intelligent agent....
s - IA implemented with adaptive fuzzy logicFuzzy logicFuzzy logic is a form of many-valued logic; it deals with reasoning that is approximate rather than fixed and exact. In contrast with traditional logic theory, where binary sets have two-valued logic: true or false, fuzzy logic variables may have a truth value that ranges in degree between 0 and 1... - GOAL Agent Programming LanguageGOAL Agent Programming LanguageGOAL is an agent programming language for programming rational agents. GOAL agents derive their choice of action from their beliefs and goals. The language provides the basic building blocks to design and implement rational agents by means of a set of programming constructs...
- IntelligenceIntelligenceIntelligence has been defined in different ways, including the abilities for abstract thought, understanding, communication, reasoning, learning, planning, emotional intelligence and problem solving....
- Intelligent systemArtificial intelligenceArtificial intelligence is the intelligence of machines and the branch of computer science that aims to create it. AI textbooks define the field as "the study and design of intelligent agents" where an intelligent agent is a system that perceives its environment and takes actions that maximize its...
- JACK Intelligent AgentsJACK Intelligent AgentsJACK Intelligent Agents or JACK is a framework in Java for multi-agent system development. JACK Intelligent Agents was built by Agent Oriented Software Pty. Ltd. and is a third generation agent platform building on the experiences of the Procedural Reasoning System and Distributed Multi-Agent...
- Multi-agent systemMulti-agent systemA multi-agent system is a system composed of multiple interacting intelligent agents. Multi-agent systems can be used to solve problems that are difficult or impossible for an individual agent or a monolithic system to solve...
and multiple-agent system - multiple interactive agents - PEASPEASP.E.A.S. is an acronym in artificial intelligence that stands for Performance, Environment, Actuators, Sensors.-Performance:Performance is a function that measures the quality of the actions the agent did....
classification of an agent's environment - Reinforcement learningReinforcement learningInspired by behaviorist psychology, reinforcement learning is an area of machine learning in computer science, concerned with how an agent ought to take actions in an environment so as to maximize some notion of cumulative reward...
- Semantic WebSemantic WebThe Semantic Web is a collaborative movement led by the World Wide Web Consortium that promotes common formats for data on the World Wide Web. By encouraging the inclusion of semantic content in web pages, the Semantic Web aims at converting the current web of unstructured documents into a "web of...
- making data on the Web available for automated processing by agents - Simulated realitySimulated realitySimulated reality is the proposition that reality could be simulated—perhaps by computer simulation—to a degree indistinguishable from "true" reality. It could contain conscious minds which may or may not be fully aware that they are living inside a simulation....
- Social simulationSocial simulationSocial simulation is a research field that applies computational methods to study issues in the social sciences. The issues explored include problems in sociology, political science, economics, anthropology, geography, archaeology and linguistics ....