The Automatic Programming of Agents that Learn Mental Models and Create Simple Plans of Action

An essential component of an intelligent agent is the ability to notice, encode, store, and utilize information about its environment. Traditional approaches to program induction have focused on evolving functional or reactive programs. This paper presents MAPMAKER, a method for the automatic generation of agents that discover information about their environment, encode this information for later use, and create simple plans utilizing the stored mental models. In this method, agents are multi-part computer programs that communicate through a shared memory. Both the programs and the representation scheme are evolved using genetic programming. An illustrative problem of 'gold' collection is used to demonstrate the method in which one part of a program makes a map of the world and stores it in memory, and the other part uses this map to find the gold The results indicate that the method can evolve programs that store simple representations of their environments and use these representations to produce simple plans.

[1]  Walter Alden Tackett,et al.  Recombination, selection, and the genetic construction of computer programs , 1994 .

[2]  Richard K. Belew,et al.  Evolving networks: using the genetic algorithm with connectionist learning , 1990 .

[3]  David Andre,et al.  The Evolution of Agents that Build Mental Models and Create Simple Plans Using Genetic Programming , 1995, ICGA.

[4]  David Andre.  Learning and upgrading rules for an OCR system using genetic programming , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[5]  Gilbert Syswerda,et al.  Uniform Crossover in Genetic Algorithms , 1989, ICGA.

[6]  J. K. Kinnear,et al.  Advances in Genetic Programming , 1994 .

[7]  David Andre,et al.  Evolution of mapmaking: learning, planning, and memory using genetic programming , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[8]  Illah R. Nourbakhsh,et al.  Time-Saving Tips for Problem Solving with Incomplete Information , 1993, AAAI.

[9]  Una-May O'Reilly,et al.  Genetic Programming II: Automatic Discovery of Reusable Programs. , 1994, Artificial Life.

[10]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[11]  David H. Ackley,et al.  Interactions between learning and evolution , 1991 .

[12]  Astro Teller,et al.  The evolution of mental models , 1994 .

[13]  Astro Teller,et al.  Turing completeness in the language of genetic programming with indexed memory , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[14]  Kalyanmoy Deb,et al.  A Comparative Analysis of Selection Schemes Used in Genetic Algorithms , 1990, FOGA.