Software Agents

• Why do we need agents?– Increasingly networked, temporary

connectivity increasing (wireless).– Data overload (e-mail, web pages, fax, …).– Greater exchange of digital information– Increasingly dependent upon electronic

sources of information.– Desire to be ‘better informed’.

• Inadequacy of current tools• Browsers are user driven• ‘Friendly’ software becoming more difficult to

use (e.g. MS Word!)• WWW too polluted for casual browsing,

intelligent search tools required; even search engines beginning to fail us!

• Coverage, web pages exploiting indexing algorithms of engines, broken links.

• Need software solution (agents) that can act in our place:

• can interact with (say) Internet data sources• can process e-mail, voice, fax and other

electronic message sources• can communicate with other agents• can accurately represent our needs and

preferences in the networked information environment

• can negotiate

• So, what is a software agent? Has characteristics:

• Something that acts on behalf of another• Is sociable, capable of meaningful interaction

with other agents (and humans)• Can make decisions on our behalf• Is capable of adapting to changing

environments and learning from user interaction

• Is mobile

• “An agent is an entity that:• acts on behalf of others in an autonomous

fashion• performs its actions in some level of

proactivity and reactivity• exhibits some levels of the key attributes of

learning, co-operation, and mobility.”• Eg:- Travel agents

• They can be classified according to: the tasks they perform; their control architecture; the range and effectiveness of their actions; the range of sensitivity of their senses; or how much internal state they posses; characteristics they show:autonomy, learning, and cooperation;

• Autonomy :an agent can operate on its own without the need for human guidance

• Proactive :ability to take the initiative rather than acting simply in response to its environment

• Cooperation with other agents is necessary to accomplish a complicated task

• an agent must posses a social ability that allows it to interact with other agents

• an agent is intelligent if it is able to learn and sense as it acts and reacts to its external environment

• “Intelligent software agents are defined as being a software program that can perform specific tasks for a user and possessing a degree of intelligence that permits it to performs parts of its tasks autonomously and to interact with its environment in a useful manner.”

• In the Internet agents possess:• efficiency: agent is given goal and returns the

result• effectiveness: agent can terminate search

when acceptable solution found• transparency and optimization: correlation

between multiple data sources possible => higher quality results

Interface agents• Interface agents perform tasks for their owners

by emphasizing autonomy and learning• a personal assistant who is collaborating with the

user in the same work environment• They support and provide assistance to a user

learning to use a particular application• By observing and imitating the user• Through receiving positive and negative feedback

from the user• By receiving explicit instructions from the user• By asking other agents for advice

Collaborative agents

• Collaboration between individuals requires that communication links be established and used effectively

• Distributed Artificial Intelligence is concerned with a virtual society of problem solvers (agents) interacting to solve a common problem

• The goal of collaborative agents is to interconnect separately developed collaborative agents, thus enabling the ensemble to function beyond the capabilities of any of its members.

Information agents

• Internet agents• explosive growth of information on the Word-

Wide Web• help us manage, manipulate, or collate

information from many distributed resources• We carry out actions that may consume long

time (e.g. searching the Web for information)• Why does not the computer (e.g. An

information agent) carries out such tasks for us and later on present us with the results?

Reactive agents

• Reactive Agents act and respond in a stimulus-response manner to the present state of the environment in which they are embedded

• reactive agent is viewed as a collection of modules which operate autonomously and responsible for specific tasks (e.g. sensing, computation, etc.).

Hybrid agents• Hybrid Agents refer to those agents whose

constitution is a combination of two or more agent philosophies within a singular agent

• These philosophies may be mobile, interface, information, collaborative, … etc.

• The goal of having hybrid agents: the benefits availed from having the combination of philosophies within a single agent is greater than the gains obtained from the same agent based on a singular philosophy

• An example of this is collaborative interface agents

Agent typology• A typology refers to the study of types of entities.• Agents may be classified based on many dimensions:• Mobility-able to move around a network-static &

mobile agents• Deliberative agents-agents possess an internal

symbolic, reasoning model and they engage in planning and negotiation in order to achieve coordination with other agents; Reactive agents-they act using a stimulus/response type of behaviour by responding to the present state of the environment in which they are embedded

• Primary attributes like autonomy, learning & cooperation

Agent Topology

• Topological theory of intelligent agent networks provides crucial information about the structure of agent distribution over a network

• It also considers agent communication, mobility and intelligence in a network

• Applications of multi-agent systems have been arising in many areas

• This has led to a set of important research problems concerning how an agent network should be designed to perform efficiently and effectively, which required the need of deciding topologies

• An agent topology must follow the specific characteristics of network, which includes: mobility, intelligence and flexibility

• Distributed Artificial Intelligence-a sub-field of Artificial Intelligence-concerned with a society of problem solvers or agents interacting in order to solve a common problem that are beyond their capabilities-computers and persons, sensors, aircraft, robots, etc.

• Such a society is termed a Multi-Agent System(MAS)• (a) solve problems that may be too large for a

centralised single agent, (b) provide enhanced speed and reliability and (c) tolerate uncertain data and knowledge.

• The problem solving performed by agents in a MAS is termed Distributed Problem Solving

• To solve common problems coherently, the agents must communicate amongst themselves, coordinate their activities and negotiate once they find themselves in conflict.

• Conflicts can result from simple limited resource contention to more complex issue-based computations-agents disagree because of discrepancies between their domains of expertise.

• Coordination-determines organisational structure amongst a group of agents, task and resource allocation

• negotiation is required for the detection and resolution of conflicts.