Loading ...
Sorry, an error occurred while loading the content.

Re: Simple question regarding task environment

Expand Messages
  • ³ÂÓí
    I think you are right. Because the environment also our program, rather than a real-world s thing. kind regards chenyu ... actuators as ... environment you ...
    Message 1 of 4 , Apr 23, 2004
    • 0 Attachment
      I think you are right. Because the environment also our program,
      rather than a real-world's thing.


      kind regards
      chenyu



      --- In aima-talk@yahoogroups.com, Mauricio Amaral de Almeida
      <malmeida@i...> wrote:
      > Someon please correct me if I wrong, but in my interpretation the
      actuators as
      > in conceptualy part of the agent.
      > But when you make a software implementation on the pair agent-
      environment you
      > have to implement the actuatror, and the sensor for that matter, as
      methods
      > of the class environment.
      > That is so for you to be able to decouple the agent and the
      environment. In
      > that way when an agent want to act over an environment it should
      call the
      > proper method in the class environment.
      > This is in fact the best way to do this because doing things this
      way the
      > agent doesn't need to know the environment internal structure.
      >
      > Mauricio
      >
      >
      > On Monday 19 April 2004 23:25, Bob Riley wrote:
      > > I am starting on some of the computing exercises in chapter 2 and
      > > have a question regarding task environment. According to the
      book,
      > > task environment is specified by performance measure, environment,
      > > actuators, and sensors. The 1st two of these I can understand -
      but
      > > why are acuators and sensors included in the task environment?
      > > Shouldn't the task environment be the elements of interest outisde
      > > of the agent? Aren't sensors and actuators part of the agent
      > > itself? Upon first seeing this, I thought that my interpretation
      of
      > > agent may be wrong - maybe the agent is simply the
      program/function
      > > and the actuators and sensors are external entities that the agent
      > > interacts with. But there are several examples in this chapter
      > > where the actuators and sensors are considered to be part of the
      > > agent. Can someone clear this up? Is it just me or does the book
      > > seem to be altering the definition of agent in different parts of
      > > the chapter?
      > >
      > > Thanks,
      > >
      > > Bob
      > >
      >
      > --
      > Prof. Dr. Maurício Amaral de Almeida
      > malmeida@i...
    Your message has been successfully submitted and would be delivered to recipients shortly.