Let us call a non-deterministic incremental algorithm one that is able to construct any solution to a combinatorial problem by selecting incrementally an ordered sequence of choices that denes this solution, each c hoice being made non-deterministically. In that case, the state space can be represented as a tree, and a solution is a path from the root of… (More)
Coevolutionary learning, which involves the embedding of adaptive learning agents in a tness environment that dynamically responds to their progress, is a potential solution for many technological chicken and egg problems. However, several impediments have t o b e o v ercome in order for coevolution-ary learning to achieve continuous progress in the long… (More)
We recently solved the two spirals problem, a diicult neural network benchmark classiication problem, using the genetic programming primi-tives set up by Koza, 1992]. Instead of using absolute tness, we use a relative tness based on a competition for coverage of the data set. This is a form of co-evolutionary search because the tness function changes with… (More)
In the eld of Operation Research and Artii-cial Intelligence, several stochastic search algorithms have been designed based on the theory of global random search (Zhigljavsky 1991). Basically , those techniques iteratively sample the search space with respect to a probability distribution which is updated according to the result of previous samples and some… (More)
Reflexive Monte-Carlo search uses the Monte-Carlo search of a given level to improve the search of the upper level. We describe the application to Morpion Solitaire. For the non touching version, reflexive Monte-Carlo search breaks the current record and establishes a new record of 78 moves.
In the eld of optimization and machine learning techniques, some very ecient and promising tools like Genetic Algorithms (GAs) and Hill-Climbing have been designed. In this same eld, the Evolving Non-Determinism (END) model presented in this paper proposes an inventive way to explore the space of states that, using the simulated \incremental" co-evolution… (More)
This paper describes a new sampling-based heuristic for tree search named SAGE and presents an analysis of its performance on the problem of grammar induction. This last work has been inspired by the Abbadingo DFA learning competition  which took place between Mars and November 1997. SAGE ended up as one of the two winners in that competition. The… (More)
In this paper, we propose that learning complex behaviors can be achieved in a coevolutionary environment where one population consists of the human users of an interactive adaptive software tool and the " opposing " population is artificial, generated by a coevolu-tionary learning engine. We take advantage of the Internet, a connected community where… (More)