GC: n
CT: An intelligent agent is a software that assists people and act on their behalf. Intelligent agents work by allowing people to delegate work that they could have done, to the agent software. Agents can perform repetitive tasks, remember things you fo rgot, intelligently summarize complex data, learn from you and even make recommendations to you.
S: UMD – http://groups.engin.umd.umich.edu/CIS/course.des/cis479/projects/agent/Intelligent_agent.html (last access: 30 December 2014)
N: 1. – intelligent (adj): c.1500, a back-formation from intelligence or else from Latin intelligentem (nominative intelligens), present participle of intelligere, earlier intellegere (see intelligence). Intelligent design, as a name for an alternative to atheistic cosmology and the theory of evolution, is from 1999. Related: Intelligently.
– agent (n): agent (n): late 15c., “one who acts,” from Latin agentem (nominative agens) “effective, powerful,” present participle of agere “to set in motion, drive, lead, conduct”).
2. All agents are autonomous, which means that an agent has control over its own actions. All agents are also goal-driven. Agents have a purpose and act accordance with that purpose. There are several ways of making goals known to an agent, and are listed below:
- An agent could be driven by a script with pre-defines action which would then define the agent’s goals.
- An agent could also be a program and as long as the program is driven by goals and has other characteristics of agents.
- An agent could also be driven by rules, and the rules would define the agent’s goals.
- There is also embedded agent goals, such as “planning” methodologies, and in some cases the agent could change its own goals over time.
An agent could also senses changes in its environment and responds to these changes. This characteristic of the agent is at the core of delegation and automation. For example, you tell your assistant “when x happens, do y” and the agent is always wai ting for x to happen. An agent continue to work even when the user is gone, which means that an agent could run on a server, but in some cases, an agent run on the user systems.
In a Multi-Agent System, agents are social, this means that they communicate with other agents. Some agents learn or change their behavior base on their previous experiences. Some agents are mobile, meaning they move from machine to machine to be clo ser to data they may need to process and do so without network delays. Finally, some agents attempt to be believable, such that they are represented as an entity visible or audible to the user and may even have aspects of emotion or personality. .
S: 1. OED – https://www.etymonline.com/search?q=intelligent+agent (last access: 30 December 2014). 2. UMD – http://groups.engin.umd.umich.edu/CIS/course.des/cis479/projects/agent/Intelligent_agent.html (last access: 30 December 2014).
SYN:
S:
CR: artificial intelligence, automation, computational intelligence, computer science, deep learning, intelligent system, virtual personal assistant.
