Introduction Genetic programming is a domain-independent problem-solving approach in which computer programs are evolved to solve, or approximately solve, problems. Genetic programming is based on the Darwinian principle of reproduction and survival of the fittest and analogs of naturally occurring genetic operations such as crossover (sexual recombination) and mutation. John Holland's pioneering Adaptation in Natural and Artificial Systems (1975) described how an analog of the evolutionary process can be applied to solving mathematical problems and engineering optimization problems using what is now called the genetic algorithm (GA). The genetic algorithm attempts to find a good (or best) solution to the problem by genetically breeding a population of individuals over a series of generations. In the genetic algorithm, each individual in the population represents a candidate solut

Parallel Distributed Genetic Programming (PDGP) is a new form of Genetic Programming (GP) suitable for the development of programs with a high degree of parallelism. Programs are represented in PDGP as graphs with nodes representing functions and terminals, and links representing the flow of control and results.

This chapter describes Parallel Distributed Genetic Programming (PDGP), a form of Genetic Programming (GP) which is suitable for the development of programs with a high degree of parallelism and an ecient and effective reuse of partial results. Programs are represented in PDGP as graphs with nodes representing functions and terminals, and links representing the flow of control and results. In the simplest form of PDGP links are directed and unlabelled, in which case PDGP can be considered a generalisation of standard GP. However, more complex representations can be used, which allow the exploration of a large space of possible programs including standard tree-like programs, logic networks, neural networks, recurrent transition networks, finite state automata, etc.

This paper describes PDGP (Parallel Distributed Genetic Programming), a new form of genetic programming which is suitable for the development of fine-grained parallel programs. PDGP is based on a graph-like representation for parallel programs which is manipulated by crossover and mutation operators which guarantee the syntactic correctness of the offspring. The paper describes these operators and reports some preliminary results obtained with this paradigm

Parallel Distributed Genetic Programming (PDGP) is a new form of genetic programming suitable for the development of parallel programs in which symbolic and neural processing elements can be combined in a free and natural way. This paper describes the representation for programs and the genetic operators on which PDGP is based. Experimental results on the XOR problem are also reported. 1

Genetic programming provides a useful paradigm for developing multiagent systems in the domains where human programming alone is not sufficient to take into account all the details of possible situations. However, existing GP methods attempt to evolve collective behavior immediately from primitive actions. More realistic tasks require several emergent behaviors and a proper coordination of these is essential for success. We have recently proposed a framework, called fitness switching, to facilitate learning to coordinate composite emergent behaviors using genetic programming. Coevolutionary fitness switching described in this chapter extends our previous work by introducing the concept of coevolution for more effective implementation of fitness switching. Performance of the presented method is evaluated on the table transport problem and a simple version of simulated robot soccer problem. Simulation results show that coevolutionary fitness switching provides an effective mechanism for learning complex collective behaviors which may not be evolved by simple genetic programming. Evolving complex collective behaviors is an interesting problem for distributed intelligence and artificial life. Some tasks can be done faster or more easily by dividing them up among

This paper describes a new challenge problem for the automatic programming of software agents, a virtual version of the quidditch game invented by J. K. Rowling in her best-selling Harry Potter books (Rowling and Grandpre, 1998; Rowling and Whisp, 2001). Good performance in this game requires adaptive control in a complex, heterogeneous, and dynamic 3-dimensional environment. In this short paper we briefly describe virtual quidditch and the challenges that it presents. A quidditch simulator environment is currently being developed; when it is complete it will be made publicly available. 1 VIRTUAL WORLDS FOR AGENT DEVELOPMENT/EVOLUTION Several technical challenges face the designer of a control system for an agent in a complex, dynamic environment. While the ultimate goal for many researchers is the development of techniques that will enable autonomous agents to perform well in the real (physical) world, the di#culties and expense involved in robotics experimentation has ...

Genetic Programming(GP) is a technique that can be used to automatically program computers to perform some required task. The technique is a kind of genetic algorithm in which the rep-resentation is a program parse tree instead of a bit-string and the fitness of each parse trees is evaluated by executing the computer program that it represents. The subject of this thesis is to investigate the use of GP to automatically program multiagent systems. To achieve this goal, we consider the general problems in creating multiagent systems, and show how GP can be used to provide solutions to many of them. Our key contributions are as follows: We show that it possible to evolve multi-agent systems using GP that: exhibit coordinated, coherent behaviour communicate explicitly, and in doing so decide what to communicate and how can resolve conflicts can be integrated into an existing society of agents We also consider the scalability problems involved in the use of GP, both generally and in par-

This paper describes the application of Parallel Distributed Genetic Programming (PDGP) to the problem of inducing programs for natural language processing. PDGP is a new form of Genetic Programming (GP) which is suitable for the development of programs with a high degree of parallelism and an efficient and effective reuse of partial results. Programs are represented in PDGP as graphs with nodes representing functions and terminals, and links representing the flow of control and results. PDGP allows the exploration of a large space of possible programs including standard tree-like programs, logic networks, neural networks, finite state automata, Recursive Transition Networks (RTNs), etc. The paper describes the representations, the operators and the interpreters used in PDGP, and illustrates its behaviour on the problem of inducing RTN-based recognisers for natural language from positive and negative examples. 1 Introduction In Genetic Programming [10, 11] programs are expressed as pa...

Genetic programming is a relatively new domain-independent method for evolving computer programs to solve problems. This chapter suggests avenues for possible future research on genetic programming, opportunities to extend the technique, and areas for possible practical applications.