Skip to content
Last Dictionary
Plane
Core ConceptsSymbolic & Classical AIAgents & HarnessesHistory & Landmarks

intelligent agent

nounAlso: rational agent, autonomous agent

In plain wordsIn AI theory, a decision-maker, such as a robot, a self-driving car, a chess program or a helpful piece of software, that notices what is going on around it and responds in ways that serve its goals.

  1. 1

    AI theory

    A system that runs a continual cycle of sensing and acting: it takes in information about its environmentenvironment, n.: Everything an AI agent interacts with but does not control — a game, a simulator, a website, the physical world. It answers each of the agent's actions with a new situation and, in reinforcement learning, a score. through sensors or data feeds, decides what to do, and changes the environment through actuators or outputs, its success judged against goals or a performance measure. Stuart Russell and Peter Norvig's textbook makes rationality the standard: given what it has perceived so far and what it knew at the outset, an agent should choose the action expected to score best on that measure. The same book orders agent designs from simple reflex agents through model-based, goal-based and utility-based agents to learning agents, and sorts task environments by properties such as observability, determinism, whether episodes are independent and the number of agents. The concept frames AI as the engineering of good decision-makers rather than the imitation of human thought.

    Model the thermostat as a simple reflex agent and the warehouse robot as a utility-based intelligent agent.

  2. 2

    Software (1990s)

    An autonomous program acting on a user's behalf, such as a mail filter, shopping bot or personal-information manager. Michael Wooldridge and Nicholas Jennings characterized such agents by autonomy, reactivity, pro-activeness and social ability, meaning the capacity to interact with other agents or with people.

Origin

The agent framing grew out of 1980s research on distributed AI and autonomous systems. Two 1995 publications consolidated the term: Wooldridge and Jennings's survey 'Intelligent Agents: Theory and Practice', and Russell and Norvig's textbook Artificial Intelligence: A Modern Approach, which made the intelligent agent the unifying concept of the field. Modern language-model AI agentsAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done. inherit the vocabulary.

Usage note

The theoretical notion is very broad: even a thermostat qualifies as a trivial agent. 'Intelligent' refers to rational choice of actions, not humanlike thought or consciousness. Today AI agentAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done. usually means a language-model-based system, a narrower and more concrete sense.

Related

See also
  • agentagent, n.: Something that acts. In AI, a program that observes its situation and takes actions toward a goal: a game-playing learner, a software helper, or a chatbot that uses tools to complete tasks.
  • AI agentAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done.
  • environmentenvironment, n.: Everything an AI agent interacts with but does not control — a game, a simulator, a website, the physical world. It answers each of the agent's actions with a new situation and, in reinforcement learning, a score.
  • multi-agent systemmulti-agent system, n.: A setup in which several AI agents, each with its own role or point of view, work together — or compete — on a problem, passing messages and results among themselves.
  • Markov decision processMarkov decision process, n.: A mathematical description of a step-by-step decision problem: each step you pick an action, receive a reward and then land in a new situation, drawn at random from odds that depend only on the current situation and your choice.
  • cognitive architecturecognitive architecture, n.: A blueprint for a complete thinking system — how memory, attention, learning and decision-making fit together — used both to build general AI agents and to model how the human mind works.
  • artificial intelligenceartificial intelligence, n.: Computer systems that do things we would normally credit to a thinking mind, such as holding a conversation, reading an X-ray or planning a route, and the field of research that builds them.
Contrast with
  • tool AItool AI, n.: AI built to be used like an instrument, answering, suggesting or calculating when asked, rather than pursuing goals on its own. Some argue that this is the only kind we should build.
  • oracle AIoracle AI, n.: An AI kept to answering questions, without acting in the world on its own. Proposed as a safer kind of superintelligence, though its answers could still steer the people who read them.

Sources

  1. Wooldridge, M. & Jennings, N. R. (1995). Intelligent Agents: Theory and Practice. Knowledge Engineering Review, 10(2), 115–152.
  2. Russell, S. & Norvig, P. (1995). Artificial Intelligence: A Modern Approach. Prentice Hall.

Mentioned in

AI agentAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done., artificial intelligenceartificial intelligence, n.: Computer systems that do things we would normally credit to a thinking mind, such as holding a conversation, reading an X-ray or planning a route, and the field of research that builds them., actuatoractuator, n.: The 'muscle' of a machine: a motor or similar device that turns electrical, hydraulic or air power into movement, such as turning a robot's joint or closing its gripper., agentagent, n.: Something that acts. In AI, a program that observes its situation and takes actions toward a goal: a game-playing learner, a software helper, or a chatbot that uses tools to complete tasks., bounded rationalitybounded rationality, n.: The idea that real decision-makers, whether people or machines, cannot consider every option or compute the perfect choice, so they make reasonable decisions within limits of time, information and thinking power., perceptionperception, n.: How an AI system or robot turns raw sensor signals, such as camera pixels, microphone sound or laser scans, into an understanding of what is around it: objects, people, words and distances., Peter NorvigPeter Norvig, prop. n.: An American computer scientist who co-wrote the standard AI textbook, led research at Google, and helped show that simple methods trained on huge amounts of data often beat clever hand-built ones., Stuart RussellStuart Russell, prop. n.: A British computer scientist who co-wrote the standard AI textbook and argues that AI must be redesigned to stay uncertain about what humans want, so that it remains under human control., utility functionutility function, n.: A way of scoring every possible outcome by how much someone, or some AI, wants it. A rational agent is often modeled as choosing whatever maximizes its expected score.