1

Intelligent Agents

Software analog to human agents real estate agent, librarian, salesperson

Perform tasks individually, or in collaborationStatic and mobileCommunicate via messages or notLearn preferences over time

2

Working definitionsAn agent is a reusable software component that provides controlled access to (shared) services and resources. Example: a printer agent that provides printing services schedules requests to a shared printer.

Agents are the basic building blocks for applications, and applications are organized as networks of collaborating agents. Example: a desktop agent "recruits" the services of a screen and a connection agent to physically connect a call.

The behavior of each agent is constrained by policies which are set by higher-level agents (security, load balancing, user prefs etc.). Example: 60% of the calls over a trunk are made by one user agent.

3

Differences from conventional programs

Agents are autonomous, that is they act on behalf of the user Agents contain some level of intelligence, from fixed rules to learning engines that allow them to adapt to changes in the environment Agents don't only act reactively, but sometimes also proactively Agents have social ability, that is they communicate with the user, the system, and other agents as required Agents may also cooperate with other agents to carry out more complex tasks than they themselves can handle Agents may move from one system to another to access remote resources or even to meet other agents

4

Usage

Simplifying distributed computingAgents as intelligent resource managers Overcoming user interface problemsAgents as personal assistants which adapt to the user This is another important motivation for agent research: convergence in AI research.

 

5

Nwana's classification

1. Mobility: static or mobile 2. Reasoning model: deliberative or

reactive 3. Ideal attributes: autonomy, learning

and cooperation 4. Role: information, management 5. Hybrid: combination of the above

Source: H. Nwana, Software Agents: An Overview

6

Nwana's classification

7

Architecture

8

Collaborative agentsModular (eg, interface, task and information agents) Agents negotiate in order to resolve conflicts (eg, meeting time) Some agents collaborate to integrate information Agents wrap around legacy systems ("glue" to interconnect them)

Provide solutions to inherently distributed problems

airtraffic control

telecommunications network management

9

RETSINA Collaboration model

10

Interface AgentsSupport and provide assistance. Cooperates with the user in accomplishing some task in an application. Interface agents learn:

by observing and imitating the user (from user) through receiving feedback from the user by receiving explicit instructions by asking other agents for advice (from peers)

Filters (eg, your email) Eager assistant (eg Open Sesame) Social filtering (referrals)

11

Information Filtering

Individual Recommendation Agents

Fine grained (users treated as individuals)Driven by attributes of users and products, therefore can recommend new products

WebWatcher

12

Collaborative Filtering

CF: Items I interacted with are compared to Items other people interacted with

Assumes you are like others (requires others)Requires interaction history prior to recommendation

Amazon.com, Group Lens

13

Interface Agents

14

Information Agents

Manage the explosive growth of information. Manipulate or collate information from many distributed sources. Examples: intelligent wrappers.Challenge: ontologies for annotating Web pages (eg, SHOE). Information agents can be mobile or static.

15

Information Agents

16

Mobile agentsPrograms that can migrate from one machine to another. Execute in a platform-independent execution environment (requirement of places). Practical but non-functional advantages:

Reduced communication cost (eg, from PDA) Asynchronous computing (when you are not connected)

Two types:One-hop mobile agents (migrate to one other place) Multi-hop mobile agents (roam the network from place to place)

Applications: Distributed information retrieval.

Telecommunication network routing.