際際滷

際際滷Share a Scribd company logo
CA 7B3
SOFTWARE AGENTS
INTERACTING WITH AGENTS
AGENT FROM DIRECT MANIPULATION
TO DELEGATION
Presenters:
BHEEMRAJ SAINI  205113009
SRISHTI GUPTA  205114001
AJAY BENIWAL  205114002
AKHILESH CHOUDHARY  205114003
PARAKH KUMAR RAHANGDALE  205114004
Date: July 18, 2016
What is an Agent?What is an Agent?
 An agent is anything that can be viewed
as perceiving its environment through
sensors and acting upon that environment
through effectors.
Formal DefinitionsFormal Definitions
 Autonomous agents are computational
systems that inhabit some complex dynamic
environment, sense and act autonomously in
this environment, and by doing so realize a
set of goals or tasks for which they are
designed. [Maes, 1995]
 Intelligent agents continuously perform three
functions: perception of dynamic conditions in
the environment; action to affect conditions in
the environment; and reasoning to interpret
perceptions, solve problems, draw
inferences, and determine actions. [Hayes-
Roth, 1995]
Agents PropertiesAgents Properties
[Brenner et al., 1998]
ReactivityReactivity
 A reactive system is one that maintains an
ongoing interaction with its environment,
and responds to changes that occur in it
(in time for the response to be useful)
ProactivenessProactiveness
 Reacting to an environment is easy (e.g., stimulus
 response rules)
 But we generally want agents to do things for us
 Hence goal directed behavior
 Pro-activeness = generating and attempting to
achieve goals; not driven solely by events; taking
the initiative
Social AbilitySocial Ability
 The real world is a multi-agent environment:
we cannot go around attempting to achieve
goals without taking others into account
 Some goals can only be achieved with the
cooperation of others
 Social ability in agents is the ability to interact
with other agents (and possibly humans) via
some kind of agent-communication language,
and perhaps cooperate with others
Other PropertiesOther Properties
 Mobility: the ability of an agent to move around an electronic
network
 Veracity  honesty: an agent will not knowingly communicate false
information
 Benevolence  kind: agents do not have conflicting goals, and that
every agent will therefore always try to do what is asked of it
 Rationality: agent will act in order to achieve its goals, and will not
act in such a way as to prevent its goals being achieved - at least
insofar as its beliefs permit
 Learning/adaption: agents improve performance over time
CharacteristicsCharacteristics
Cooperation (Proactive)
Autonomy Adaptation
(Learning)
Smart agent
[Nwana, 1996]
Adaptation
 Agents adapt to their
environment and
users and learn from
experience.
 Via machine learning,
knowledge discovery,
data mining, etc.
 Situated in and aware
of their environment
Cooperation
Autonomy Adaptation
Cooperation
 Agents use standard
languages and protocols
to cooperate and
collaborate to achieve
common goals.
 Cooperate with human
agents and other
software agents
 Supported by agent
communication
languages and protocols.
 Consistent with human
conventions and intuition.
Cooperation
Autonomy Adaptation
Autonomy
 Agents act
autonomously to
pursue their agenda.
 Goal directed
behavior
Cooperation
Autonomy Adaptation
Task Modeling in Intelligent AgentsTask Modeling in Intelligent Agents
 Before we design an intelligent agent, we
must specify its task environment:
PEAS:
Performance measure
Environment
Actuators
Sensors
PEAS Description
of Task Environments
Performance
Measures
Environment
Actuators
Sensors
used for high-level characterization of agents
determine the actions the agent
can perform
surroundings beyond the
control of the agent
used to evaluate how well an
agent solves the task at hand
provide information about the
current state of the environment
Example: Agent = Taxi DriverExample: Agent = Taxi Driver
 Performance measure: Safe, fast, legal,
comfortable trip, maximize profits
 Environment: Roads, other traffic,
pedestrians, customers
 Actuators: Steering wheel, accelerator,
brake, signal, horn
 Sensors: Cameras, speedometer, GPS,
odometer, engine sensors
Example: Agent = Medical DiagnosisExample: Agent = Medical Diagnosis
SystemSystem
 Performance measure: Correct Diagnosis,
minimize costs
 Environment: Patient, hospital, staff
 Actuators: Screen display (questions,
tests, diagnoses, treatments, referrals)
 Sensors: Keyboard (entry of symptoms,
findings, patient's answers)
How Might People Interact with
Agents?
How will intelligent agents interact with
people and perhaps more important, how
might people think about agents?
Agents might set up schedules, reserve hotel
and meeting rooms, arrange transportation,
and even outline meeting topics, all without
human intervention.
Safety
Making sure that the agent does not do things that
would jeopardize the physical, mental, or
monetary well-being of the owner.
 The sense of control, but because the technical
and social implications are considerably
different, it deserves its own special
consideration.
 Privacy and confidentiality of actions will be
among the major issues confronting the use of
intelligent agents in our future of a fully
interconnected, fully communicating society.
Privacy
Human-Agent Interaction
The manner by which the person's
conceptual model of the agent's method
of operation and activities is presented,
and the manner by which the agent offers
advice and information to the person.
What is Delegation?
Delegation is the assignment of responsibility to
another person for the purpose of carrying out
specific job-related activities. Delegation is a
shift of decision-making authority from one
organizational level to another.
Elements of Delegation
a 'principal'
 An individual who delegates
authority over a particular policy
area (or function) to another
an 'agent'.
 The other person who receives the
delegated authority
Knowing When to Delegate
Delegating can be especially helpful in the
following situations:
 When the task offers valuable training to an
employee
 When an employee has more knowledge or
experience related to the task than you
 When the task is recurring and all employees should
be prepared or trained
 When the task is of low priority and you have high
priority tasks that require your immediate attention
To Whom Should You Delegate?
When deciding who to select for the task, you
must consider:
 The current work load of the employee
 The employees strengths and weaknesses
 The training and experience levels of the
employee
Agent from Direct Manipulation
to Delegation
 Delegation gives users the option to offload tasks
to software systemsagentsthat perform the
tasks for the user.
 This enables users to perform tasks that are
difficult to perform using graphical user
interfaces, tasks such as searching and retrieving
data in large distributed networks
Benefits of Delegation
 Manager / Supervisor Benefits
 Reduced stress
 Improved time management
 Increased trust
 Employee Benefits
 Professional knowledge and skill development
 Elevated self-esteem and confidence
 Sense of achievement
 Organizational Benefits
 Increased teamwork
 Increased productivity and efficiency
Steps in Delegation
I  Introduce the task
D- Demonstrate clearly what needs to be done
E - Ensure understanding
A - Allocate authority, information and resources
L - Let go
S - Support and Monitor
Introduce the Task
 Determine the task to
be delegated
 Determine the tasks
to retain
 Select the delegate
Demonstrate Clearly
 Show examples of previous
work
 Explain objectives
 Discuss timelines, set
deadlines
Ensure Understanding
 Clear communication
 Ask for clarification
 Secure commitment
Allocate
authority, information, resources
 Provide access to all information sources
 Provide appropriate training to ensure
success
Let go
 Communicate delegates authority
 Step back, let them work
Support and Monitor
 Schedule follow-up meetings
 Review progress
 Assist, when requested
 Avoid interference
 Publicly praise progress and completion
 Encourage problem solving
References
[1]: Jeffrey M. Bradshaw, Software Agents, MIT Press, 2000
[2]: http://www.javaworld.com/javaworld/jw-04-1997/jw-04-agents.html
[3]: http://www.msci.memphis.edu/~franklin/AgentProg.html
[4]: http://www.javaworld.com/javaworld/jw-04-1997/jw-04-hood.html
[5]: http://www.trl.ibm.co.jp/aglets/JAAPI-whitepaper.html
[6]: http://luckyspc.lboro.ac.uk/Docs/Papers/Mesela97.html
[7]: http://www.javaworld.com/javaworld/jw-05-1997/jw-05-hood.html
[8]: http://www.trl.ibm.co.jp/aglets/whitepaper.htm
[9]: http://www.networking.ibm.com/iag/iaghome.html#new

More Related Content

Group 1 (3009, 01, 02, 03, 04) interacting with agents, direct manipulation to delegation

  • 2. INTERACTING WITH AGENTS AGENT FROM DIRECT MANIPULATION TO DELEGATION Presenters: BHEEMRAJ SAINI 205113009 SRISHTI GUPTA 205114001 AJAY BENIWAL 205114002 AKHILESH CHOUDHARY 205114003 PARAKH KUMAR RAHANGDALE 205114004 Date: July 18, 2016
  • 3. What is an Agent?What is an Agent? An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through effectors.
  • 4. Formal DefinitionsFormal Definitions Autonomous agents are computational systems that inhabit some complex dynamic environment, sense and act autonomously in this environment, and by doing so realize a set of goals or tasks for which they are designed. [Maes, 1995] Intelligent agents continuously perform three functions: perception of dynamic conditions in the environment; action to affect conditions in the environment; and reasoning to interpret perceptions, solve problems, draw inferences, and determine actions. [Hayes- Roth, 1995]
  • 6. ReactivityReactivity A reactive system is one that maintains an ongoing interaction with its environment, and responds to changes that occur in it (in time for the response to be useful)
  • 7. ProactivenessProactiveness Reacting to an environment is easy (e.g., stimulus response rules) But we generally want agents to do things for us Hence goal directed behavior Pro-activeness = generating and attempting to achieve goals; not driven solely by events; taking the initiative
  • 8. Social AbilitySocial Ability The real world is a multi-agent environment: we cannot go around attempting to achieve goals without taking others into account Some goals can only be achieved with the cooperation of others Social ability in agents is the ability to interact with other agents (and possibly humans) via some kind of agent-communication language, and perhaps cooperate with others
  • 9. Other PropertiesOther Properties Mobility: the ability of an agent to move around an electronic network Veracity honesty: an agent will not knowingly communicate false information Benevolence kind: agents do not have conflicting goals, and that every agent will therefore always try to do what is asked of it Rationality: agent will act in order to achieve its goals, and will not act in such a way as to prevent its goals being achieved - at least insofar as its beliefs permit Learning/adaption: agents improve performance over time
  • 11. Adaptation Agents adapt to their environment and users and learn from experience. Via machine learning, knowledge discovery, data mining, etc. Situated in and aware of their environment Cooperation Autonomy Adaptation
  • 12. Cooperation Agents use standard languages and protocols to cooperate and collaborate to achieve common goals. Cooperate with human agents and other software agents Supported by agent communication languages and protocols. Consistent with human conventions and intuition. Cooperation Autonomy Adaptation
  • 13. Autonomy Agents act autonomously to pursue their agenda. Goal directed behavior Cooperation Autonomy Adaptation
  • 14. Task Modeling in Intelligent AgentsTask Modeling in Intelligent Agents Before we design an intelligent agent, we must specify its task environment: PEAS: Performance measure Environment Actuators Sensors
  • 15. PEAS Description of Task Environments Performance Measures Environment Actuators Sensors used for high-level characterization of agents determine the actions the agent can perform surroundings beyond the control of the agent used to evaluate how well an agent solves the task at hand provide information about the current state of the environment
  • 16. Example: Agent = Taxi DriverExample: Agent = Taxi Driver Performance measure: Safe, fast, legal, comfortable trip, maximize profits Environment: Roads, other traffic, pedestrians, customers Actuators: Steering wheel, accelerator, brake, signal, horn Sensors: Cameras, speedometer, GPS, odometer, engine sensors
  • 17. Example: Agent = Medical DiagnosisExample: Agent = Medical Diagnosis SystemSystem Performance measure: Correct Diagnosis, minimize costs Environment: Patient, hospital, staff Actuators: Screen display (questions, tests, diagnoses, treatments, referrals) Sensors: Keyboard (entry of symptoms, findings, patient's answers)
  • 18. How Might People Interact with Agents? How will intelligent agents interact with people and perhaps more important, how might people think about agents? Agents might set up schedules, reserve hotel and meeting rooms, arrange transportation, and even outline meeting topics, all without human intervention.
  • 19. Safety Making sure that the agent does not do things that would jeopardize the physical, mental, or monetary well-being of the owner. The sense of control, but because the technical and social implications are considerably different, it deserves its own special consideration. Privacy and confidentiality of actions will be among the major issues confronting the use of intelligent agents in our future of a fully interconnected, fully communicating society. Privacy
  • 20. Human-Agent Interaction The manner by which the person's conceptual model of the agent's method of operation and activities is presented, and the manner by which the agent offers advice and information to the person.
  • 21. What is Delegation? Delegation is the assignment of responsibility to another person for the purpose of carrying out specific job-related activities. Delegation is a shift of decision-making authority from one organizational level to another.
  • 22. Elements of Delegation a 'principal' An individual who delegates authority over a particular policy area (or function) to another an 'agent'. The other person who receives the delegated authority
  • 23. Knowing When to Delegate Delegating can be especially helpful in the following situations: When the task offers valuable training to an employee When an employee has more knowledge or experience related to the task than you When the task is recurring and all employees should be prepared or trained When the task is of low priority and you have high priority tasks that require your immediate attention
  • 24. To Whom Should You Delegate? When deciding who to select for the task, you must consider: The current work load of the employee The employees strengths and weaknesses The training and experience levels of the employee
  • 25. Agent from Direct Manipulation to Delegation Delegation gives users the option to offload tasks to software systemsagentsthat perform the tasks for the user. This enables users to perform tasks that are difficult to perform using graphical user interfaces, tasks such as searching and retrieving data in large distributed networks
  • 26. Benefits of Delegation Manager / Supervisor Benefits Reduced stress Improved time management Increased trust Employee Benefits Professional knowledge and skill development Elevated self-esteem and confidence Sense of achievement Organizational Benefits Increased teamwork Increased productivity and efficiency
  • 27. Steps in Delegation I Introduce the task D- Demonstrate clearly what needs to be done E - Ensure understanding A - Allocate authority, information and resources L - Let go S - Support and Monitor
  • 28. Introduce the Task Determine the task to be delegated Determine the tasks to retain Select the delegate
  • 29. Demonstrate Clearly Show examples of previous work Explain objectives Discuss timelines, set deadlines
  • 30. Ensure Understanding Clear communication Ask for clarification Secure commitment
  • 31. Allocate authority, information, resources Provide access to all information sources Provide appropriate training to ensure success
  • 32. Let go Communicate delegates authority Step back, let them work
  • 33. Support and Monitor Schedule follow-up meetings Review progress Assist, when requested Avoid interference Publicly praise progress and completion Encourage problem solving
  • 34. References [1]: Jeffrey M. Bradshaw, Software Agents, MIT Press, 2000 [2]: http://www.javaworld.com/javaworld/jw-04-1997/jw-04-agents.html [3]: http://www.msci.memphis.edu/~franklin/AgentProg.html [4]: http://www.javaworld.com/javaworld/jw-04-1997/jw-04-hood.html [5]: http://www.trl.ibm.co.jp/aglets/JAAPI-whitepaper.html [6]: http://luckyspc.lboro.ac.uk/Docs/Papers/Mesela97.html [7]: http://www.javaworld.com/javaworld/jw-05-1997/jw-05-hood.html [8]: http://www.trl.ibm.co.jp/aglets/whitepaper.htm [9]: http://www.networking.ibm.com/iag/iaghome.html#new