A Simulation of Adaptive Agents in Hostile Environment   [AA]

by

Haynes, T., D. and Wainwright, R., L.

Literature search on Evolutionary ComputationBBase ©1999-2013, Rasmus K. Ursem
     Home · Search · Adv. search · Authors · Login · Add entries   Webmaster
Note to authors: Please submit your bibliography and contact information - online papers are more frequently cited.

Info: Proceedings of the 1995 ACM Symposium on Applied Computing (Conference proceedings), 1995, p. 318-323
Keywords:genetic algorithms, genetic programming
Abstract:
In this paper we use the genetic programming technique to evolve programs to control [GP] an autonomous agent capable of learning how to survive in a hostile environment. In order to facilitate this goal, agents are run through random environment configurations. Randomly generated programs, which control the interaction of the agent with its environment, are recombined to form better programs. Each generation of the population of agents is placed into the Simulator with the ultimate goal of producing an agent capable of surviving any environment. The environment that an agent is presented consists of other agents, mines, and energy. The goal of this research is to construct a program which when executed will allow an agent (or agents) to correctly sense, and mark, the presence of items (energy and mines) in any environment. The Simulator determines the raw fitness of each agent by interpreting the associated program. General programs are evolved to solve this problem. Different environmental setups are presented to show the generality of the solution. These environments include one agent in a fixed environment, one agent in a fluctuating environment, and multiple agents in a fluctuating environment cooperating together. The genetic programming technique [GP] was extremely successful. The average fitness per generation in all three environments tested showed steady improvement. Programs were successfully generated that enabled an agent to handle any possible environment.
Notes:
Agent has access to memory holding information on locations it has already visited. Agents are run through random environment configurations. Environment contains other agents, lethal mines and energy. Agents aims to sense and mark these. One example: multiple agents cooperating in a fluctating environment. GP generated an "agent to handle any possible enironment".
URL(s):Postscript
(G)zipped postscript

Review item:

Mark as doublet (will be reviewed)

Print entry




BibTex:
@InProceedings{Hayes:1995:agents,
  author =       "Thomas D. Haynes and Roger L. Wainwright",
  title =        "A Simulation of Adaptive Agents in Hostile
                 Environment",
  booktitle =    "Proceedings of the 1995 ACM Symposium on Applied
                 Computing",
  year =         "1995",
  editor =       "K. M. George and Janice H. Carroll and Ed Deaton and
                 Dave Oppenheim and Jim Hightower",
  pages =        "318--323",
  address =      "Nashville, USA",
  publisher =    "ACM Press",
  keywords =     "genetic algorithms, genetic programming",
  URL =          "http://euler.mcs.utulsa.edu/~haynes/sac95.ps",
  size =         "8 pages",
  abstract =     "In this paper we use the genetic programming technique
                 to evolve programs to control an autonomous agent
                 capable of learning how to survive in a hostile
                 environment. In order to facilitate this goal, agents
                 are run through random environment configurations.
                 Randomly generated programs, which control the
                 interaction of the agent with its environment, are
                 recombined to form better programs. Each generation of
                 the population of agents is placed into the Simulator
                 with the ultimate goal of producing an agent capable of
                 surviving any environment. The environment that an
                 agent is presented consists of other agents, mines, and
                 energy. The goal of this research is to construct a
                 program which when executed will allow an agent (or
                 agents) to correctly sense, and mark, the presence of
                 items (energy and mines) in any environment. The
                 Simulator determines the raw fitness of each agent by
                 interpreting the associated program. General programs
                 are evolved to solve this problem. Different
                 environmental setups are presented to show the
                 generality of the solution. These environments include
                 one agent in a fixed environment, one agent in a
                 fluctuating environment, and multiple agents in a
                 fluctuating environment cooperating together. The
                 genetic programming technique was extremely successful.
                 The average fitness per generation in all three
                 environments tested showed steady improvement. Programs
                 were successfully generated that enabled an agent to
                 handle any possible environment.",
  notes =        "Agent has access to memory holding information on
                 locations it has already visited.

                 Agents are run through random environment
                 configurations. Environment contains other agents,
                 lethal mines and energy. Agents aims to sense and mark
                 these. One example: multiple agents cooperating in a
                 fluctating environment. GP generated an {"}agent to
                 handle any possible enironment{"}.",
}