1 / 20

Intelligent Agents

Intelligent Agents. Software agents. Monday: Overview video (Introduction to software agents) Agents and environments Rationality Wednesday: PEAS (Performance measure, Environment, Actuators, Sensors ) Example of simple and not-so-simple software agents Friday: Environment types

yehuda
Download Presentation

Intelligent Agents

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Intelligent Agents

  2. Software agents • Monday: • Overview video (Introduction to software agents) • Agents and environments • Rationality • Wednesday: • PEAS (Performance measure, Environment, Actuators, Sensors) • Example of simple and not-so-simple software agents • Friday: • Environment types • Agent types • Group discussion

  3. Very short software agents overview • http://labcast.media.mit.edu/?p=23 • What is an agent?: A computer program that is • Embodied (i.e local) • Situated (ie. has knowledge of / responds to its situation / environment) • Autonomous (i.edecides what action to take based on its own situation) • Cooperating (i.e can communicate with other agents to achieve tasks)

  4. Agent and environments

  5. Agent and environments • Agents include humans, robots, softbots, thermostats, etc. • The agent function maps from percept histories to actions: f: P -> A • The agent program runs on the physical architecture to produce f

  6. Vacuum-cleaner world • Percepts: location and contents, e.g., [A;Dirty] • Actions: Left, Right, Suck, NoOp

  7. A vacuum-cleaner agent

  8. Pseudocode What is the right function? Can it be implemented in a small agent program?

  9. Rationality • Fixed performance measure evaluates the environment sequence • one point per square cleaned up in time T? • one point per clean square per time step, minus one per move? • penalize for > k dirty squares? • A rational agent chooses whichever action maximizes the expected value of the performance measure given the percept sequence to date • Rational is different from omniscient • percepts may not supply all relevant information • Rational is different from clairvoyant • action outcomes may not be as expected • Rational is different from successful • Rational exploration, learning, autonomy

  10. PEAS • To design a rational agent, we must specify the task environment. Example: consider, e.g., the task of designing an automated taxi: • Performance measure: • Environment: • Actuators: • Sensors:

  11. Another example • Internet shopping agents: • Performance measure?? • Environment?? • Actuators?? • Sensors??

  12. Environment types • The environment type largely determines the agent design • The real world is (of course) partially observable, stochastic, sequential, dynamic, continuous, multi-agent

  13. Agent types • Four basic types in order of increasing generality: • Simple reflex agents • Reflex agents with state • Goal-based agents • Utility-based agents

  14. Simple reflex agents

  15. Reflex agents with state

  16. Goal-based agents

  17. Utility-based agents

  18. Learning agents

  19. Example • Simple example • Demonstration of software agent on Linux • Complex example: • http://web.media.mit.edu/~hugo/demos/commonsense-aria.html

  20. Summary • Agents interact with environments through actuators and sensors • The agent function describes what the agent does in all circumstances • The performance measure evaluates the environment sequence • A perfectly rational agent maximizes expected performance • Agent programs implement (some) agent functions • PEAS descriptions definetaskenvironments • Environments are categorized along several dimensions: • observable? deterministic? episodic? static? discrete? single-agent? • Several basic agent architectures exist: • Reflex, reflex with state, goal-based, utility-based

More Related