1 / 29

Intelligent Agents

Intelligent Agents. CPS 4801-01. Outline. Agents and environments PEAS (Performance measure, Environment, Actuators, Sensors) Environment types Agent types. Agents. An AI program = An intelligent Agent

zeal
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 CPS 4801-01

  2. Outline • Agents and environments • PEAS (Performance measure, Environment, Actuators, Sensors) • Environment types • Agent types

  3. Agents • An AI program = An intelligent Agent • An agent is anything that can be viewed as perceiving its environment though sensors and acting upon that environment though actuators. • Perception-Action Cycle

  4. Application of Intelligent Agents • AI has successfully been used in • Finance? • Robotics? • Games? • Medicine? • The Web?

  5. AI in Finance Stock Market Bonds Commodities Market Trading Agent Rates News Trades

  6. AI in Robotics • Physical actuators Environment Cameras Microphones Robot Touch Motors: wheels, legs, arms, grippers Voice

  7. AI in Games • Chess game • Characters in games You Game Agent Your moves Its own moves

  8. AI in Medicine You Diagnostic Agent Vital Signals: blood pressures, heart signals Doctor Diagnostics

  9. Simple Diagnostic Expert System: • http://familydoctor.org/familydoctor/en/health-tools/search-by-symptom.html

  10. AI and the Web World Wide Web Crawler Web Pages DB Query You

  11. Percept: the agent’s perceptual inputs at any given instant • Percept Sequence: the complete history of everything the agent has ever perceived • The agent function maps from percept histories to actions: [f: P* A] (abstract) • The agent program runs on the physical architecture to produce f. (implementation)

  12. Vacuum-Cleaner World • Percepts: location and contents, e.g., [A, Dirty] • Actions: Left, Right, Suck, NoOp

  13. A Vacuum-Cleaner Agent

  14. A Vacuum-Cleaner Agent • function REFLEX-VACUUM-AGENT ([location,status]) returns an action ifstatus = Dirty then return Suck else if location = A then return Right else if location = B then return Left

  15. Task Environment • PEAS: Performance measure, Environment, Actuators, Sensors • Consider the task of designing an automated taxi: • Performance measure: safety, destination, profits, legality, comfort… • Environment: US streets/freeways, traffic, pedestrians, weather… • Actuators: steering, accelerator, brake, horn, speaker/display… • Sensors: camera, sonar, GPS, odometer, engine sensor…

  16. Internet Shopping Agent • Performance measure? • Environment? • Actuators? • Sensors?

  17. Internet Shopping Agent • Performance measure? price, quality, appropriateness, efficiency • Environment? WWW sites, vendors, shippers • Actuators? display to user, follow URL, fill in form • Sensors? HTML pages (text, graphics, scripts)

  18. Environment Types • Fully observable (vs. partially observable): An agent’s sensors give it access to the complete state of the environment at each point in time. • Card game vs. poker (needs internal memory) • Deterministic (vs. stochastic): The next state of the environment is completely determined by the current state and the action executed by the agent. • Chess vs. game with dice (uncertainty, unpredictable) • Episodic (vs. sequential): The agent’s experience is divided into atomic “episodes” (each episode consists of the agent perceiving and then performing a single action), and the choice of action in each episode depends only on the episode itself. • Chess and taxi driving

  19. Environment Types • Static (vs. dynamic): The environment is unchanged while an agent is deliberation. (The environment is semidynamic if the environment itself does not change with the passage of time but the agent’s performance score does.) • Taxi driving vs. chess (when played with a clock) vs. crossword puzzles • Discrete (vs. continuous): A limited number of distinct, clearly defined percepts and actions. • Chess vs. taxi driving (infinite) • Single agent (vs. multiagent): An agent operating by itself in an environment. • Crossword puzzle vs. chess

  20. The real world is (of course) partially observable, stochastic, sequential, dynamic, continuous, multi-agent.

  21. Agent Types • Four basic types: • - simple reflex agents • - model-based reflex agents • - goal-based agents • - utility-based agents • All these can be turned into learning agents.

  22. Simple Reflex Agents

  23. Model-Based Reflex Agents

  24. Goal-Based Agents

  25. Utility-Based Agents

  26. Learning Agents

  27. Summary • Agents interact with environments though actuators and sensors. • The agent function describes what the agent does in all circumstances. • Agent programs implement agent functions. • PEAS descriptions define task environments. • Environment 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

  28. Try out some intelligent agents! • AChatbotis a computer program designed to simulate an intelligent conversation with one or more human users via auditory or textual methods, primarily for engaging in small talk. • ALICE: http://alice.pandorabots.com/ • Won the Loebner Prize three times (in 2000, 2001 and 2004) • ELIZA: http://nlp-addiction.com/eliza/ • One of the classic chat bots, written at MIT by Joseph Weizenbaum between 1964 and 1966 • Automated online assistants

More Related