Review 1 - RoboCode controllers (Karthik Gopalratnam)

From: Karthik Gopalratnam (karthikg_at_cs.washington.edu)
Date: Sun Oct 19 2003 - 23:40:16 PDT

  • Next message: Alan L. Liu: "Paper Review: Evolving Robot Tank Controllers"

    "Evolving Robot Tank Controllers" - Jacob Eisenstein

       This paper discusses the application of genetic programming to
    design automatically evolving tank controllers for the RoboCode
    environment.

      Given that the author deals with designing robot controllers that
    evolve based on genetic programming techniques, the main ideas in the
    paper deal with formulating the problem in the genetic algorithms
    framework: developing an efficient representation scheme, and an
    effective evaluation strategy.
      The paper presents a representation of robots in a REX-like language,
    that achieves the twofold goal of representing different robot
    controllers efficiently for the genetic algorithm, as well as enable
    the evaluation of successive generations of controllers in an efficient
    manner since the representation is merely interpreted by Java code, as
    opposed to having to be compiled into bytecode for each evaluation.
       Also presented are various methods of evaluating the effectiveness
    of various controllers within the robocode framework.

       The choice of fitness measure is not mathematically rigorous, ie.
    there does not appear to be a formally quantifiable reason why the
    evaluation measure used against a certain set of opponents should work
    against an opponent that that controller has never encountered before.

       The fact that the most effective learned robots did not learn to use
    their guns to shoot is apparently an enourmous anomaly in this method.
    Although the author makes a case for the fact that this seems to be an
    anomaly because using the gun is merely intuitive from a human's
    perspecitve, it seems that there are significant mathematically
    quantifable gains to a controller that can use its weapon efectively at
    least a small fraction of the time, since a single correct shot not
    only diminishes the opponent's energy level, it also increases the
    controller's energy.
       This limitation seems to be a consequence of the fact that the
    representation is circumscribed by the limitations of genetic
    algorithms in general - there might not be an efficient way of
    representing the trigonometric information required to evolve
    controllers capable of predicting where the opponent is going to move,
    and when and in what direction to shoot etc., while also being able to
    maipulate these individual controllers in the context of mutations,
    crossovers etc. Imroving the representation for genetic algorithms is
    an important, open research question.
        Another open research area that woudld be worth pursuing is to
    determine whether learning better controllers is possible using neural
    networks. The author makes a strong case for using neural networks to
    overcome the difficulty of targeting, and the whether neural networks
    combined with biiologically inspired learning techniques will generate
    the best controllers remains to be seen.


  • Next message: Alan L. Liu: "Paper Review: Evolving Robot Tank Controllers"

    This archive was generated by hypermail 2.1.6 : Sun Oct 19 2003 - 23:40:16 PDT