Berbicara tentang Agent

March 18, 2012

sumber: http://homepages.ius.edu/rwisman/C463/html/Chapter2.htm

Definitions

  • Agent – Anything that perceives its environment through sensors and acts upon that environment through actuators.
  • Percept – An agent’s perceptual inputs at a given instant.
  • Percept sequence  – Complete history of percepts.

  • Performance measure, embodies the criterion for success of an agent’s actions.
  • Environment
  • Actuators
  • Sensors

Environment types

  • Fully/partially observable – fully observable if can sense entire environment.
  • Deterministic/stochastic (nondeterministic) – deterministic if next state completely determined by current state and agent action; otherwise stochastic.
  • Episodic/sequential – episodic if next episode does not depend on previous episodes; sequential if current decision can affect future decisions.
  • Static/dynamic – dynamic if environment can change after agent senses but before agent acts.
  • Discrete/continuous – how time is handled; how environment changes over time and agent percepts and actions. If time is not a factor then discrete.
  • Single/multi agent – multi-agents may compete or cooperate (e.g. two agents playing chess or a pilot and flight controller agent flying airplane).

Agents and Environments

  • Agents include humans, robots, softbots, thermostats, …
  • Agent function maps from percept histories to actions A:f : P* g A
  • Agent program runs on the physical architecture of a computer to perform f

Vacuum-cleaner world

  • Perceptslocation and status, e.g. [A, Dirty]
  • Actions: Left, Right, Suck, NoOp
Performance measure might maximize cleaning and minimize travel.

The Structures of Agents

Four basic types in order of increasing generality:

  • simple reflex agents – select action based on current percept, ignoring percept history.
  • reflex agents with state – select action based on percept history
  • goal-based agents – select action to achieve some goal
  • utility-based agents – select action that achieves best measure of succes

All above can also be learning agents that analyze experience to select action.

  • Program = algorithm + data
  • Agent program implements agent function mapping percepts to actions: f : P* g A
  • Architecture is the computing device with sensors and actuators
  • Agent = architecture + program

 

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: