Miguel Nicolau

Genetic Algorithms Using Grammatical Evolution

This paper describes the GAUGE system, Genetic Algorithms Using Grammatical Evolution. GAUGE is a position independent Genetic Algorithm that uses Grammatical Evolution with an attribute grammar to dictate what position a gene codes for. GAUGE suffers from neither under-specification nor over-specification, is guaranteed to produce syntactically correct individuals, and does not require any repair after the application of genetic operators.GAUGE is applied to the standard onemax problem, with results showing that its genotype to phenotype mapping and position independence nature do not affect its performance as a normal genetic algorithm. A new problem is also presented, a deceptive version of the Mastermind game, and we show that GAUGE possesses the position independence characteristics it claims, and outperforms several genetic algorithms, including the competent genetic algorithm messyGA.

Evolving genes to balance a pole

We discuss how to use a Genetic Regulatory Network as an evolutionary representation to solve a typical GP reinforcement problem, the pole balancing. The network is a modified version of an Artificial Regulatory Network proposed a few years ago, and the task could be solved only by finding a proper way of connecting inputs and outputs to the network. We show that the representation is able to generalize well over the problem domain, and discuss the performance of different models of this kind.

Evolving behaviour trees for the Mario AI competition using grammatical evolution

This paper investigates the applicability of Genetic Programming type systems to dynamic game environments. Grammatical Evolution was used to evolved Behaviour Trees, in order to create controllers for the Mario AI Benchmark. The results obtained reinforce the applicability of evolutionary programming systems to the development of artificial intelligence in games, and in dynamic systems in general, illustrating their viability as an alternative to more standard AI techniques.

π Grammatical Evolution

πGrammatical Evolution is presented and its performance on four benchmark problems is reported. πGrammatical Evolution is a position-independent variation on Grammatical Evolution’s genotype-phenotype mapping process where the order of derivation sequence steps are no longer applied to nonterminals in a predefined fashion from left to right on the developing program. Instead the genome is used to specify which nonterminal will be developed next, in addition to specifying the rule that will be applied to that nonterminal. Results suggest that the adoption of a more flexible mapping process where the order of non-terminal expansion is not determined a-priori, but instead itself evolved, is beneficial for Grammatical Evolution.

Introducing Grammar Based Extensions for Grammatical Evolution

This paper presents a series of extensions to standard grammatical evolution. These grammar-based extensions facilitate the exchange of knowledge between genotype and phenotype strings, thus establishing a better correlation between the search and solution spaces, typically separated in grammatical evolution. The results obtained illustrate the practical advantages of these extensions, both in terms of convenience and potential increase in performance.

Solving sudoku with the GAuGE system

This paper presents an evolutionary approach to solving Sudoku puzzles. Sudoku is an interesting problem because it is a challenging logical puzzle that has previously only been solved by computers using various brute force methods, but it is also an abstract form of a timetabling problem, and is scalably difficult. A different take on the problem, motivated by the desire to be able to generalise it, is presented. The GAuGE system was applied to the problem, and the results obtained show that its mapping process is well suited for this class of problems.

A non-destructive grammar modification approach to modularity in grammatical evolution

Modularity has proven to be an important aspect of evolutionary computation. This work is concerned with discovering and using modules in one form of grammar-based genetic programming, grammatical evolution (GE). Previous work has shown that simply adding modules to GEs grammar has the potential to disrupt fit individuals developed by evolution up to that point. This paper presents a solution to prevent the disturbance in fitness that can come with modifying GEs grammar with previously discovered modules. The results show an increase in performance from a previously examined grammar modification approach and also an increase in performance when compared to standard GE.

On the Evolution of Scale-Free Topologies with a Gene Regulatory Network Model

A novel approach to generating scale-free network topologies is introduced, based on an existing artificial gene regulatory network model. From this model, different interaction networks can be extracted, based on an activation threshold. By using an evolutionary computation approach, the model is allowed to evolve, in order to reach specific network statistical measures. The results obtained show that, when the model uses a duplication and divergence initialisation, such as seen in nature, the resulting regulation networks not only are closer in topology to scale-free networks, but also require only a few evolutionary cycles to achieve a satisfactory error value.

Experiments in program synthesis with grammatical evolution: A focus on Integer Sorting

We present the results of a series of investigations where we apply a form of grammar-based genetic programming to the problem of program synthesis in an attempt to evolve an Integer Sorting algorithm. The results confirm earlier research in the field on the difficulty of the problem given a primitive set of functions and terminals. The inclusion of a swap(i, j) function in combination with a nested for loop in the grammar enabled a successful solution to be found in every run. We suggest some future research directions to overcome the challenge of evolving sorting algorithms from primitive functions and terminals.

Evolutionary Behavior Tree Approaches for Navigating Platform Games

Computer games are highly dynamic environments, where players are faced with a multitude of potentially unseen scenarios. In this paper, AI controllers are applied to the Mario AI benchmark platform, by using the grammatical evolution system to evolve behavior tree structures. These controllers are either evolved to both deal with navigation and reactiveness to elements of the game or used in conjunction with a dynamic A* approach. The results obtained highlight the applicability of behavior trees as representations for evolutionary computation and their flexibility for incorporation of diverse algorithms to deal with specific aspects of bot control in game environments.